Large vocabulary continuous speech recognition using HTK

Woodland, Philip C.; Odell, JJ; Valtchev, V.; Young, Steve

doi:10.1109/icassp.1994.389562

Cited by 166 publications

(86 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results are similar to those achieved by other systems that use the same database but different parameterization (e. g. Vicente-Peña et al (2006b), Woodland et al (1994) or Parihar and Picole (2001)). In the remainder of this section, we show the performance of our proposals for each database under noisy conditions.…”

Section: Resultssupporting

confidence: 79%

Uncertainty decoding on Frequency Filtered parameters for robust ASR

Vicente-Peña

Díaz-de-María

2010

Speech Communication

View full text Add to dashboard Cite

The use of feature enhancement techniques to obtain estimates of the clean parameters is a common approach for robust automatic speech recognition (ASR). However, the decoding algorithm typically ignores how accurate these estimates are. Uncertainty decoding methods incorporate this type of information. In this paper, we develop a formulation of the uncertainty decoding paradigm for Frequency Filtered (FF) parameters using spectral subtraction as a feature enhancement method. Additionally, we show that the uncertainty decoding method for FF parameters admits a simple interpretation as a spectral weighting method that assigns more importance to the most reliable spectral components.Furthermore, we suggest combining this method with SSBD-HMM (Spectral Subtraction and Bounded Distance HMM), one recently proposed technique that is able to compensate for the effects of features that are highly contaminated (outliers). This combination pursues two objectives: to improve the results achieved by uncertainty decoding methods and to determine which part of the improvements is due to compensating for the effects of outliers and which part is due to compensating for other less deteriorated features.

show abstract

Section: Resultssupporting

confidence: 79%

Uncertainty decoding on Frequency Filtered parameters for robust ASR

Vicente-Peña

Díaz-de-María

2010

Speech Communication

View full text Add to dashboard Cite

show abstract

“…It is well known (Alleva et al, 1992;Woodland et al, 1994;Beyerlein et al, 1997) that the word accuracy can be improved significantly by the use of across-word phoneme models.…”

Section: Across-word Models and Searchmentioning

confidence: 99%

Fast Search for Large Vocabulary Speech Recognition

Kanthak

Sixtus

Molau

et al. 2000

Artificial Intelligence

View full text Add to dashboard Cite

Abstract. In this article we describe methods for improving the RWTH German speech recognizer used within the VERBMOBIL project. In particular, we present acceleration methods for the search based on both within-word and across-word phoneme models. We also study incremental methods to reduce the response time of the online speech recognizer. Finally, we present experimental off-line results for the three VERBMOBIL scenarios. We report on word error rates and real-time factors for both speaker independent and speaker dependent recognition.

show abstract

“…The SI-284 set of the Wall Street Journal (WSJ) corpus [20] is formed by combining data from WSJ0 and WSJ1 databases, sampled at 16 kHz. The set contains 36,416 sequences, representing around 80 hours of speech.…”

Section: Databasesmentioning

confidence: 99%

Convolutional Neural Networks-based continuous speech recognition using raw speech signal

Palaz

Magimai.-Doss

Collobert

2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

144

View full text Add to dashboard Cite

State-of-the-art automatic speech recognition systems model the relationship between acoustic speech signal and phone classes in two stages, namely, extraction of spectral-based features based on prior knowledge followed by training of acoustic model, typically an artificial neural network (ANN). In our recent work, it was shown that Convolutional Neural Networks (CNNs) can model phone classes from raw acoustic speech signal, reaching performance on par with other existing feature-based approaches. This paper extends the CNN-based approach to large vocabulary speech recognition task. More precisely, we compare the CNN-based approach against the conventional ANN-based approach on Wall Street Journal corpus. Our studies show that the CNN-based approach achieves better performance than the conventional ANN-based approach with as many parameters. We also show that the features learned from raw speech by the CNN-based approach could generalize across different databases.

show abstract

Large vocabulary continuous speech recognition using HTK

Cited by 166 publications

References 4 publications

Uncertainty decoding on Frequency Filtered parameters for robust ASR

Uncertainty decoding on Frequency Filtered parameters for robust ASR

Fast Search for Large Vocabulary Speech Recognition

Convolutional Neural Networks-based continuous speech recognition using raw speech signal

Contact Info

Product

Resources

About