Speech Recognition

This paper proposes an efficient linguistic processing strategy for speech recognition and understanding using a dependency structure grammar. The strategy includes parsing and phrase prediction algorithms. After speech processing and …...

Speech recognition systems incorporate a language model which, at each stage of the recognition task, assigns a probabil- ity of occurrence to each word in the vocabulary. A class of …...

Performance in speech recognition systems has progressed to the point where it is now realistic to begin integrating speech with natural language systems to produce spoken language systems. Two factors …...

SRI has developed a new architecture for integrating speech and natural-language processing that applies linguistic constraints during recognition by incrementally expanding the state-transition network embodied in a unification grammar. We …...

SRI and U.C. Berkeley have begun a cooper- ative effort to develop a new architecture for real-time implementation of spoken language systems (SLS). Our goal is to develop fast speech …...

This paper presents a study of military applications of advanced speech processing technology which includes three major elements: (1) review and assessment of cur- rent efforts in military applications of …...

A model-based spectral estimation algorithm is derived that improves the robustness of speech recognition systems to additive noise. The algorithm is tailored for filter-bank-based systems, where the estimation should seek …...

This paper presents a human-machine dia- logue model in the field of task-oriented dialogues. The originality of this model resides in the clear separation of dialogue knowledge from task knowl- …...

This paper describes recent work on the Unisys ATIS Spo- ken Language System, and reports benchmark results on nat- ural language, spoken language, and speech recognition. We describe enhancements to …...

This paper presents speech recognition test results from the BBN BYBLOS system on the Feb 91 DARPA benchmarks in both the Resource Management (RM) and the Air Travel Information System …...

Integration of language constraints into a large vocabulary speech recognition system often leads to prohibitive complexity. We propose to factor the constraints into two components. The first is characterized by …...

This paper describes a general formalism for integrating two or more speech recognition technologies, which could be devel- oped at different research sites using different recognition strate- gies. In this …...

Language understanding work at Paramax focuses on ap- plying general-purpose language understanding technology to spoken language understanding, text understanding, and document processing, integrating language understanding with speech recognition, knowledge-based information …...

This paper describes our initial efforts at porting the VOY- AGER spoken language system to Japanese. In the process we have reorganized the structure of the system so that lan- …...

Tied-mixture (or semi-continuous) distributions are an im- portant tool for acoustic modeling, used in many high- performance speech recognition systems today. This paper provides a survey of the work in …...

This paper deals with search algorithms for real-time speech recog- nition. We argue that software-only speech recognition has several critical advantages over using special or parallel hardware. We present a …...

We show how the recognition performance of a speech recog- nition component in a speech retrieval system affects the retrieval effectiveness. A speech retrieval system facilitates content-based retrieval of speech …...

We present an integrated approach to speech and natural language processing which uses a single parser to create training for a statistical speech recognition component and for interpreting recognized text. …...

This paper explores use of synergistically-integrated systems of microphone arrays and neural networks for robust speech recognition in variable acoustic environments, where the user must not be encumbered by microphone …...

In many applications of natural language processing it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may need to determine which of …...

In this paper we demonstrate that speech recognition can be effectively applied to information retrieval (IR) applications. Our system exploits the fact that the intended words of a spo- ken …...

This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models derives from statistical models used in …...

We present the concepts of weighted language, ~ansduction and au- tomaton from algebraic automata theory as a general framework for describing and implementing decoding cascades in speech and lan- guage …...

On the observation of current available voice organizers, all of them accept only voice commands or word-based commands. Using natural spoken language to operate organizer is still a difficult problem. …...

In language modeling for speech recognition the goal is to constrain the search of the speech recognizer by providing a model which can, given a context, indicate what the next …...

We examine the Differential Grammar, a representation designed to discriminate which of a set of eonfusable alternatives is most likely in the context it occurs in. This approach is useful …...

This paper presents a novel multimodal system applied to the setup and control of distributed interactive simulations. We have developed the QuickSet prototype, a pen/voice system running on a hand-held …...

Recent empirical research has shown con- clusive advantages of multimodal interac- tion over speech-only interaction for map- based tasks. This paper describes a mul- timodal language processing architecture which supports …...

Language modeling is to associate a sequence of words with a priori probability, which is a key part of many natural language applications such as speech recognition and statisticM lna- …...

Miscommunication in speech recognition sys- tems is unavoidable, but a detailed character- ization of user corrections will enable speech systems to identify when a correction is taking place and to …...

In this article, we apply to natural language parsing and tagging the device of trigger- pair predictors, previously employed exclu- sively within the field of language mod- elling for speech …...

Language models for speech recognition con- centrate solely on recognizing the words that were spoken. In this paper, we advocate re- defining the speech recognition problem so that its goal …...

AbstractATR has built a multi-language speech translation system called ATR-MATRIX. It consists of a spoken-language translation subsystem, which is the focus of this paper, together with a highly accurate speech …...

Repetition is very common. Adaptive language models, which allow probabilities to change or adapt after seeing just a few words of a text, were introduced in speech recognition to account …...

This paper addresses recent progress in speaker-independent, large vocabulary, continuous speech recognition, which has opened up a wide range of near and mid-term applications. One rapidly ex- panding application area …...

Although there has been regular improvement in speech recog- nition technology over the past decade, speech recognition is far from being a solved problem. Most recognition systems are tuned to …...

A phonetic representation of a language is used to describe the corresponding pronunciation and synthesize the acoustic model of any vocabulary. In order to obtain better phonetic representation, context-dependent units …...

While recent retrieval techniques do not limit the number of index terms, out-of- vocabulary (OOV) words are crucial in speech recognition. Aiming at retrieving information with spoken queries, we fill …...

We consider the problem of parsing non-recursive context-free grammars, i.e., context-free grammars that generate finite languages. In natural language process- ing, this problem arises in several areas of application, including …...

Today, corpus plays an important role in development and evaluation language and speech technologies, such as part of speech tagging, parsing, word sense disambiguation, text categorization, named entity classification, information …...

Language model based IR system proposed in recent 5 years has introduced the language model approach in the speech recognition area into the IR community and improves the performance of …...

Based upon a statistically trained speech translation system, in this study, we try to combine distinctive features derived from the two modules: speech recognition and statistical machine translation, in a …...

Ngram models are simple in language modeling and have been successfully used in speech recognition and other tasks. However, they can only capture the short distance context dependency within an …...

Spelling recognition is an approach to enhance a speech recognizer’s ability to cope with incorrectly recognized words and out-of-vocabulary words. This paper presents a general framework for Thai speech recognition …...

The detection of prosodic characteristics is an im- portant aspect of both speech synthesis and speech recognition. Correct placement of pitch accents aids in more natural sounding speech, while automatic …...

Sitting at the intersection between statis- tics and machine learning, Dynamic Bayesian Networks have been applied with much success in many domains, such as speech recognition, vision, and compu- tational …...

We present an approach to multi-device dia- logue that evaluates and selects amongst candi- date dialogue moves based on features at mul- tiple levels. Multiple sources of information can be …...

The paper outlines the development and design of a speech driven control for a personal in-car navigation system which runs on a standard Pocket PC. The modified system enables speech …...

. The paper presents the design concept of the VoiceTRAN Communicator that in- tegrates speech recognition, machine translation and text-to-speech synthesis using the DARPA Galaxy architecture. The aim of the …...

This paper describes our recent work on integrating speech recognition and machine translation for improving speech translation performance. Two approaches are applied and their performance are evaluated in the workshop …...

The segment model (SM) is a family of methods that use the segmental distribution rather than frame-based density (e.g. HMM) to represent the underlying characteristics of the observation sequence. It …...

The conventional n-gram language model exploits only the immediate context of historical words without exploring long-distance semantic information. In this paper, we present a new information source extracted from latent …...

. We propose a new method to integrate multiple speech translation systems based on user interface-level integration. Users can select the result of free-sentence speech translation or that of registered …...

AbstractRecent improvements in speech recognition technology have resulted in products that can now demonstrate commercial value in a variety of applications. Many vendors are marketing products which combine ASR applications …...

It is practically impossible to build a word-based lexicon for speech recogni- tion in agglutinative languages that would cover all the relevant words. The prob- lem is that words are …...

Automatic estimation of word significance oriented for speech-based Information Re- trieval (IR) is addressed. Since the sig- nificance of words differs in IR, automatic speech recognition (ASR) performance has been …...

The paper presents the results of a project com- pleted by the authors for realizing a contin- uous speech recognition system for Bulgarian. The state-of-the-art speech recognition technol- ogy used …...

In this paper, we present a novel approach to integrate speech recognition and rule- based machine translation by lattice pars- ing. The presented approach is hybrid in two senses. First, …...

Even leaving aside concerns of cognitive plausibil- ity, incremental parsing is appealing for applications such as speech recognition and machine translation be- cause it could allow the incorporation of syntactic …...

Syllables play an important role in speech synthesis and recognition. We present sev- eral different approaches to the syllabifica- tion of phonemes. We investigate approaches based on linguistic theories of …...

Feature statistics normalization techniques have been shown to be very successful in improving the noise robustness of a speech recognition system. In this paper, we propose an associative scheme in …...

This paper explores several unsupervised ap- proaches to automatic keyword extraction using meeting transcripts. In the TFIDF (term frequency, inverse document frequency) weighting framework, we incorporated part- of-speech (POS) information, …...

AbstractIn this paper, we present the design, collection, transcription and analysis of a Mandarin Chinese Broadcast Collection of over 3000 hours. The data was collected by Hong Kong University of …...

AbstractTypical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-site reports with difficult acoustic environments. Standard …...

In situated dialogue humans often utter lin- guistic expressions that refer to extralinguistic entities in the environment. Correctly resolv- ing these references is critical yet challeng- ing for artificial agents …...

This paper is about interpreting human com- munication in meetings using audio, video and other signals. Automatic meeting recognition and understanding is extremely challenging, since communication in a meeting is …...

AbstractBuilding a comprehensive pronunciation lexicon is a crucial element in the success of any speech recognition engine. The first stage of lexicon design involves the compilation of a comprehensive word …...

AbstractWe have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research resource built using this …...

Mobile devices are becoming the dominant mode of information access despite being cumbersome to input text using small key- boards and browsing web pages on small screens. We present Qme!, …...

AbstractSpeech recognition technology suffers from a lack of robustness which limits its usability for fully automated speech-to-text transcription, and manual correction is generally required to obtain perfect transcripts. In this …...

AbstractThis paper describes recent efforts at Linguistic Data Consortium at the University of Pennsylvania to create manual transcripts as a shared resource for human language technology research and evaluation. Speech …...

AbstractAudiovisual speech recognition (AVSR) systems have been proven superior over audio-only speech recognizers in noisy environments by incorporating features of the visual modality. In order to develop reliable AVSR systems, …...

Improvements on driven decoding system combination This paper proposes an improved driven decoding method for speech recognition system combination. The combination method involves the use of auxiliary transcription as external …...

_________________________________________________________________________________________________________ Exploitation of a classification tolerance margin for improving the estimation of class-based acoustic models for speech recognition This paper presents the...

AbstractWe describe a software tool named “Speechalyzer” which is optimized to process large speech data sets with respect to transcription, labeling and annotation. It is implemented as a client server …...

Robustness and portability of spoken language understanding systems among languages and domains : the PORTMEDIA project The ANR PORTMEDIA projet aimed at complementing the MEDIA corpus so as to foster …...

AbstractWe report here on the eighth evaluation campaign organized in 2011 by the IWSLT workshop series. That IWSLT 2011 evaluation focused on the automatic translation of public talks and included …...

AbstractThe Twins corpus is a collection of utterances spoken in interactions with two virtual characters who serve as guides at the Museum of Science in Boston. The corpus contains about …...

AbstractThis contribution describes an on-going projects a smartphone application called Voice Ãpp, which is a follow-up of a previous application called Dialäkt Ãpp. The main purpose of both apps is …...

Despite the overwhelming use of statistical language models in speech recognition, machine translation, and several other domains, few high probability guarantees exist on their generaliza- tion error. In this paper, …...

AbstractString segmentation is an important and recurring problem in natural language processing and other domains. For morphologically rich languages, the amount of different word forms caused by morphological processes like …...

We propose a language modeling (LM) approach incorporating interpolated distanced n-grams in a Dirichlet class language model (DCLM) (Chien and Chueh, 2011) for speech recognition. The DCLM relaxes the bag-of-words …...

Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an in- teresting yet challenging research area. In particular, language modeling …...

Wild bird watching has become a popular leisure activity in recent years. Very often, people can see birds or hear their sounds, but have no idea what kind of bird …...

AbstractThis paper outlines the recent development on multilingual medical data and multilingual speech recognition system for network-based speech-to-speech translation in the medical domain. The overall speech-to-speech translation (S2ST) system was …...

Arabic, Hebrew, and similar languages are typi- cally written without diacritics, leading to ambigu- ity and posing a major challenge for core language processing tasks like speech recognition. Previous approaches …...

We present an approach to speech recogni- tion that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. …...

Recurrent neural network language models (RNNLM) have recently demonstrated vast potential in modelling long-term dependen- cies for NLP problems, ranging from speech recognition to machine translation. In this work, we …...

AbstractEvaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use. However, …...

AbstractWe propose two models for verbalizing numbers, a key component in speech recognition and synthesis systems. The first model uses an end-to-end recurrent neural network. The second model, drawing inspiration …...

AbstractThis work proposes a new confidence measure for evaluating text-to-speech alignment systems outputs, which is a key component for many applications, such as semi-automatic corpus anonymization, lips syncing, film dubbing, …...

AbstractMost languages have no established writing system and minimal written records. However, textual data is essential for natural language processing, and particularly important for training language models to support speech …...

AbstractWeighted finite automata and transducers (including hidden Markov models and conditional random fields) are widely used in natural language processing (NLP) to perform tasks such as morphological analysis, part-of-speech tagging, …...

This paper describes the method that was used to produce additional acoustic model training data for the less-resourced languages of Lithuanian and Latvian. The method uses existing baseline speech recognition …...

AbstractRecurrent neural networks have achieved state-of-the-art results in many artificial intelligence tasks, such as language modeling, neural machine translation, speech recognition and so on. One of the key factors to …...

AbstractIn this article, we discuss which text, speech, and image technologies have been developed, and would be feasible to develop, for the approximately 60 Indigenous languages spoken in Canada. In …...

An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech …...

Developing language resources is an important task when creating a speech recognition system for a less-resourced language. In this paper we describe available language resources and their preparation for use …...

Neural end-to-end architectures have been recently proposed for spoken language translation (SLT), following the state-of- the-art results obtained in machine transla- tion (MT) and speech recognition (ASR). Motivated by this …...

AbstractThere has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a …...

AbstractApplications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out of vocabulary words. In-depth …...

AbstractWe present a resource for computational experiments on Mapudungun, a polysynthetic indigenous language spoken in Chile with upwards of 200 thousand speakers. We provide 142 hours of culturally significant conversations …...

AbstractThe conventional paradigm in speech translation starts with a speech recognition step to generate transcripts, followed by a translation step with the automatic transcripts as input. To address various shortcomings …...

AbstractTraining objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., …...

AbstractUnsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on evaluating …...

AbstractThe CMU Wilderness Multilingual Speech Dataset (Black, 2019) is a newly published multilingual speech dataset based on recorded readings of the New Testament. It provides data to build Automatic Speech …...

AbstractAn increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to …...

Our study presents a series of experiments on speech recognition with endangered and ex- tinct Samoyedic languages, spoken in North- ern and Southern Siberia. To best of our knowledge, this …...

In this research, we developed the Taiwanese speech recognition system which used the Kaldi toolkit to implement. The Taiwanese corpus was collected by Taiwan Taiwanese National Reading Competition and Classmate …...

In order to study the effectiveness of the current deep learning-based speech recognition models in the speech recognition tasks of Taiwanese Southern Min Recommended Characters and Taiwan Minnanyu Luomazi Pinyin, …...

The automated transcription of spoken lan- guage, and meetings, in particular, is be- coming more widespread as automatic speech recognition systems are becoming more accu- rate. This trend has significantly …...

AbstractWhile Transformer-based text classifiers pre-trained on large volumes of text have yielded significant improvements on a wide range of computational linguistics tasks, their implementations have been unsuitable for live incremental …...

AbstractDue to the recent advances of natural language processing, several works have applied the pre-trained masked language model (MLM) of BERT to the post-correction of speech recognition. However, existing pre-trained …...

AbstractThis paper describes an investigation of establishing communication between a quadro- tor and a human by means of qualitative spatial relations using speech recognition. It is based on a system …...

AbstractSpeech Recognition is an active research area where advances of technology have continuously driven the development of research work. However, due to the lack of adequate resources, certain languages such …...

AbstractThis paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data …...

In the turbulent world of 2022, where mass population movements due to war and disas- ter are becoming increasingly common, lan- guage skills are more relevant than ever. Peo- ple …...

AbstractAn increasing number of papers have been addressing issues related to low-resource languages and the transcription bottleneck paradigm. After several years spent in Northern Australia, where some of the strongest …...

This paper summarizes the current state of de- velopment in improving an open source subti- tling tool. This includes improvements to the speech recognition model for German, the re- placement …...

AbstractDespite the fact that variation is a fundamental characteristic of natural language, automatic speech recognition systems perform systematically worse on non-standardised and marginalised language varieties. In this paper we use …...

AbstractInformation integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different …...

AbstractIn this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to …...

Language preservation has become increasingly urgent with globalization and rapid technological advancement. Minority languages, such as Hakka, are particularly vulnerable. This study aims to expedite the research and development of …...

Previous work has demonstrated that multilin- gual fine-tuning of a pretrained multilingual speech representation model can lead to im- proved speech recognition accuracy when there is extremely little target language …...

AbstractAppTek participated in the subtitling and formality tracks of the IWSLT 2023 evaluation. This paper describes the details of our subtitling pipeline - speech segmentation, speech recognition, punctuation prediction and …...

This study focuses on the adaptation and training of the Whisper model using the provided data and text annotations from the FSR-2023 Hakka Speech Recognition Challenge. The Whisper model is …...