Data Driven Approaches to Speech and Language Processing

Chollet, Gérard; McTait, Kevin; Petrovska‐Delacrétaz, Dijana

doi:10.1007/11520153_8

Cited by 9 publications

(5 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this aim, several non linear speech processing techniques have been proposed, such as non linear parametric and non parametric autoregressive models, speech fluid dynamics, modulation, and fractal methods. Some of these methods are theoretically discussed in this volume by Bastari et al [3], Chollet et al [7], Faundez-Zanuy [24], Haykin [33], Kubin et al [43], Murphy and Akande [46], Petek [57], and Stylianou [81]. The results are very encouraging, showing that nonlinear speech processing methods offers a good alternative to conventional speech encoding techniques.…”

Section: Nonlinearities In Speech Acousticsmentioning

confidence: 80%

Some Notes on Nonlinearities of Speech

Esposito

Marinaro

2005

Nonlinear Speech Modeling and Applications

View full text Add to dashboard Cite

Abstract. Speech is exceedingly nonlinear. Efforts to propose non-linear models of its dynamics are worth to be made but difficult to implement since nonlinearity is not easily handled from an engineering and mathematical point of view. This paper is an attempt to make accessible to untrained people the notion of nonlinearity in speech, revising several nonlinear speech phenomena and the engineering endeavour for modeling them.

show abstract

Section: Nonlinearities In Speech Acousticsmentioning

confidence: 80%

Some Notes on Nonlinearities of Speech

Esposito

Marinaro

2005

Nonlinear Speech Modeling and Applications

View full text Add to dashboard Cite

show abstract

“…As explained in [6,7,8], the set of ALISP units is automatically acquired through parametrization, temporal decomposition, vector quantization, and Hidden Markov Modeling.…”

Section: The Acquisition and Modeling Of Alisp Unitsmentioning

confidence: 99%

“…This is one of the originalities of the AL-ISP approach (Automatic Language Independent Speech Processing). ALISP tools were first developed for very low bit-rate speech coding [6], and then were successfully adapted for other tasks such as speaker [8] and language recognition [7]. Schwarz [15] showed that data-driven approaches are also applicable for music signals.…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of known advertisements in radio broadcast with data-driven ALISP transcriptions

Khemiri¹,

Chollet²,

Petrovska-Delacretaz³

2011

2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI)

View full text Add to dashboard Cite

International audienceThis paper describes an audio indexing system to search for known advertisements in radio broadcast streams, using automatically acquired segmental units. These segmental units called ALISP units are acquired automatically using temporal decomposition and vector quantization and modeled by Hidden Markov Models (HMMs). To detect commercials, ALISP transcriptions of reference advertisements are compared to those of radio stream using the Leven-shtein distance. The system is described and evaluated using broadcast streams provided by YACAST. On a set of 802 advertisements we achieve a mean precision of 95% with the corresponding recall value of 97%. The results show that the system is robust in situations where the advertisement to detect is stretched or suffer from time distortions. Moreover, this system allowed us to detect some annotation error

show abstract

“…As explained in [9,11,13,14,21], and shown in Fig. 2, the set of ALISP units is automatically acquired through parametrization, temporal decomposition, vector quantization, and Hidden Markov Modeling.…”

Section: The Acquisition and Modeling Of Alisp Unitsmentioning

confidence: 99%

“…This is the originality of the ALISP approach. ALISP is a data-driven technique that was first developed for very low bit-rate speech coding [10], and then successfully adapted for other tasks such as speaker [14] and language recognition [11]. Schwarz [23] showed that data-driven approaches are also applicable for music signals.…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of known advertisements in radio broadcast with data-driven ALISP transcriptions

Khemiri

Chollet

Petrovska‐Delacrétaz

2011

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

This paper presents an audio indexing system to search for known advertisements in radio broadcast streams, using automatically acquired segmental units. These units, called Automatic Language Independent Speech Processing (ALISP) units, are acquired using temporal decomposition and vector quantization and modeled by Hidden Markov Models (HMMs). To detect commercials, ALISP transcriptions of reference advertisements are compared to the transcriptions of the test radio stream using the Levenshtein distance. The system is described and evaluated on one day broadcast audio streams from 11 French radio stations containing 2070 advertisements. With a set of 2,172 reference advertisements we achieve a mean precision rate of 99% with the corresponding recall value of 96%. Moreover, this system allowed us to detect some annotation errors.

show abstract

Data Driven Approaches to Speech and Language Processing

Cited by 9 publications

References 84 publications

Some Notes on Nonlinearities of Speech

Some Notes on Nonlinearities of Speech

Automatic detection of known advertisements in radio broadcast with data-driven ALISP transcriptions

Automatic detection of known advertisements in radio broadcast with data-driven ALISP transcriptions

Contact Info

Product

Resources

About