Spoken language recognition-a step toward multilinguality in speech processing

Navrátil, Jǐŕı

doi:10.1109/89.943345

Cited by 72 publications

(18 citation statements)

References 18 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, cross and multilingual-based 1 Here, the word "gisting" refers to systems that identify the main topic or "gist" of the audio material. studies have also been performed for SDR [67], [68]. Advances represented by the cited BN and SDR studies notwithstanding, the NGSW database involves a level of complexity in terms of the range and extent of acoustic distortion, speaker variability, and audio quality that has not been approached in existing research.…”

Section: Introductionmentioning

confidence: 99%

SpeechFind: advances in spoken document retrieval for a National Gallery of the Spoken Word

Hansen

Huang

Zhou

et al. 2005

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

Abstract-Advances in formulating spoken document retrieval for a new National Gallery of the Spoken Word (NGSW) are addressed. NGSW is the first large-scale repository of its kind, consisting of speeches, news broadcasts, and recordings from the 20th century. After presenting an overview of the audio stream content of the NGSW, with sample audio files from U.S. Presidents from 1893 to the present, an overall system diagram is proposed with a discussion of critical tasks associated with effective audio information retrieval. These include advanced audio segmentation, speech recognition model adaptation for acoustic background noise and speaker variability, and information retrieval using natural language processing for text query requests that include document and query expansion. For segmentation, a new evaluation criterion entitled fused error score (FES) is proposed, followed by application of the CompSeg segmentation scheme on DARPA Hub4 Broadcast News (30.5% relative improvement in FES) and NGSW data. Transcript generation is demonstrated for a six-decade portion of the NGSW corpus. Novel model adaptation using structure maximum likelihood eigenspace mapping shows a relative 21.7% improvement. Issues regarding copyright assessment and metadata construction are also addressed for the purposes of a sustainable audio collection of this magnitude. Advanced parameter-embedded watermarking is proposed with evaluations showing robustness to correlated noise attacks. Our experimental online system entitled "SpeechFind" is presented, which allows for audio retrieval from a portion of the NGSW corpus. Finally, a number of research challenges such as language modeling and lexicon for changing time periods, speaker trait and identification tracking, as well as new directions, are discussed in Manuscript

show abstract

Section: Introductionmentioning

confidence: 99%

SpeechFind: advances in spoken document retrieval for a National Gallery of the Spoken Word

Hansen

Huang

Zhou

et al. 2005

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

show abstract

“…al. [10] successfully used phonotactic-acoustic features. Later Yan [9] applied a comb ination of acoustic, phonotactic and prosodic information for language identification.…”

Section: Existing Approachesmentioning

confidence: 99%

Mixed Language Speech Recognition without Explicit Identification of Language

Bhuvanagirir¹,

Kopparapu

2012

AJSP

View full text Add to dashboard Cite

Use of mixed language in day to day spoken speech is becoming common and is accepted as being syntactically correct. Ho wever mach ine recognition of mixed language spoken speech is a challenge to a conventional speech recognition engine. There are studies on how to enable recognition of mixed language speech. At one end of the spectra is to use acoustic models of the co mplete phone set of the mixed language to enable recognition wh ile on the other end of the spectra is to use a language identification module followed by language dependent speech recognition engines to do the recognition. Each of this has its own imp licat ions. In this paper, we approach the problem of mixed language speech recognition by using available resources and show that by suitably constructing an appropriate pronunciation dictionary and modifying the language model to use mixed language, one can achieve a good recognition accuracy of spoken mixed language.

show abstract

“…Discriminative ability of phone recognizers: In the PPRVSM framework, the phone recognizers are used to convert the speech into a set of phone lattices, from which the phonetic N-gram statistics are estimated to model the languages. Then the entropy of the Ngram statistics can be used to evaluate the discriminative ability of the phone lattices in language recognition [23], [24]. The conditional entropy of N-gram statistics relative to K target languages can be calculated as…”

Section: Selection Strategy For the Acoustic Diversified Phone Recognmentioning

confidence: 99%

Language Recognition Based on Acoustic Diversified Phone Recognizers and Phonotactic Feature Fusion

Deng

Zhang

et al. 2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYOne typical phonotactic system for language recognition is parallel phone recognition followed by vector space modeling (PPRVSM). In this system, various phone recognizers are applied in parallel and fused at the score level. Each phone recognizer is trained for a known language, which is assumed to extract complementary information for effective fusion. But this method is limited by the large amount of training samples for which word or phone level transcription is required. Also, score fusion is not the optimal method as fusion at the feature or model level will retain more information than at the score level. This paper presents a new strategy to build and fuse parallel phone recognizers (PPR). This is achieved by training multiple acoustic diversified phone recognizers and fusing at the feature level. The phone recognizers are trained on the same speech data but using different acoustic features and model training techniques. For the acoustic features, Mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction (PLP) are both employed. In addition, a new time-frequency cepstrum (TFC) feature is proposed to extract complementary acoustic information. For the model training, we examine the use of the maximum likelihood and feature minimum phone error methods to train complementary acoustic models. In this study, we fuse phonotactic features of the acoustic diversified phone recognizers using a simple linear fusion method to build the PPRVSM system. A novel logistic regression optimized weighting (LROW) approach is introduced for fusion factor optimization. The experimental results show that fusion at the feature level is more effective than at the score level. And the proposed system is competitive with the traditional PPRVSM. Finally, the two systems are combined for further improvement. The best performing system reported in this paper achieves an equal error rate (EER) of 1.24%, 4.98% and 14.96% on the NIST 2007 LRE 30-second, 10-second and 3-second evaluation databases, respectively, for the closed-set test condition. key words: language recognition, parallel phone recognition followed by vector space modeling (PPRVSM), acoustic diversified phone recognizers, feature fusion, logistic regression optimized weighting (LROW), timefrequency cepstrum (TFC)

show abstract

Spoken language recognition-a step toward multilinguality in speech processing

Cited by 72 publications

References 18 publications

SpeechFind: advances in spoken document retrieval for a National Gallery of the Spoken Word

SpeechFind: advances in spoken document retrieval for a National Gallery of the Spoken Word

Mixed Language Speech Recognition without Explicit Identification of Language

Language Recognition Based on Acoustic Diversified Phone Recognizers and Phonotactic Feature Fusion

Contact Info

Product

Resources

About