Towards speech rate independence in large vocabulary continuous speech recognition

Martínez, Fernando; Tapias, Daniel; Álvarez, Jorge

doi:10.1109/icassp.1998.675367

Cited by 27 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A first step toward addressing this issue, i.e., to help improve the match between the models used and the speech being processed for recognition, is to quantify the inherent speech rate variability. Then, once an estimation of the underlying speech rate is done, one could select appropriately pretrained acoustic models [25], [54] or adaptively set transition probabilities of the HMMs [4], [5] that appropriately reflect the rate of the speech being measured.…”

Section: A Significancementioning

confidence: 99%

Robust Speech Rate Estimation for Spontaneous Speech

Wang

Narayanan

2007

IEEE Trans. Audio Speech Lang. Process.

101

View full text Add to dashboard Cite

In this paper, we propose a direct method for speech rate estimation from acoustic features without requiring any automatic speech transcription. We compare various spectral and temporal signal analysis and smoothing strategies to better characterize the underlying syllable structure to derive speech rate. The proposed algorithm extends the methods of spectral subband correlation by including temporal correlation and the use of prominent spectral subbands for improving the signal correlation essential for syllable detection. Furthermore, to address some of the practical robustness issues in previously proposed methods, we introduce some novel components into the algorithm such as the use of pitch confidence for filtering spurious syllable envelope peaks, magnifying window for tackling neighboring syllable smearing, and relative peak measure thresholds for pseudo peak rejection. We also describe an automated approach for learning algorithm parameters from data, and find the optimal settings through Monte Carlo simulations and parameter sensitivity analysis. Final experimental evaluations are conducted based on a portion of the Switchboard corpus for which manual phonetic segmentation information, and published results for direct comparison are available. The results show a correlation coefficient of 0.745 with respect to the ground truth based on manual segmentation. This result is about a 17% improvement compared to the current best single estimator and a 11% improvement over the multiestimator evaluated on the same Switchboard database.

show abstract

Section: A Significancementioning

confidence: 99%

Robust Speech Rate Estimation for Spontaneous Speech

Wang

Narayanan

2007

IEEE Trans. Audio Speech Lang. Process.

101

View full text Add to dashboard Cite

show abstract

“…The acoustic changes, such as coarticulation, are modeled by directly adapting the acoustic models (or a subset of their parameters, i.e. weights and transition probabilities) to the different speaking rates (Bard et al, 2001;Martinez et al, 1998;Morgan et al, 1997;Shinozaki and Furui, 2003;Zheng et al, 2000). Most of the approaches are based on a separation of the training material into discrete speaking rate classes, which are then used for the training of rate dependent models.…”

Section: Pronunciation Modeling Techniquesmentioning

confidence: 99%

Automatic speech recognition and speech variability: A review

BenZeghiba

Mori

Deroo

et al. 2007

Speech Communication

431

207

View full text Add to dashboard Cite

Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and user satisfaction under some circumstances. This is related to several factors, such as the sensitivity to the environment (background noise), or the weak representation of grammatical and semantic knowledge.Current research is also emphasizing deficiencies in dealing with variation naturally present in speech. For instance, the lack of robustness to foreign accents precludes the use by specific populations. Also, some applications, like directory assistance, particularly stress the core recognition technology due to the very high active vocabulary (application perplexity). There are actually many factors affecting the speech realization: regional, sociolinguistic, or related to the environment or the speaker herself. These create a wide range of variations that may not be modeled correctly (speaker, gender, speaking rate, vocal effort, regional accent, speaking style, non-stationarity, etc.), especially when resources for system training are scarce. This paper outlines current advances related to these topics.

show abstract

“…These experiments were motivated by the fact that the analysis on phone duration, presented in Section 3, revealed that adults and children in the speech corpora used in this work presented a very different mean phone duration. It can be hypothesized that the effect of the speaking rate is mostly concentrated on the first and second order time derivatives of the MFCCs (Martinez et al, 1998), therefore performing mean and variance normalization of dynamic features could be useful to compensate for very different speaking rates.…”

Section: Results Ofmentioning

confidence: 99%

Towards age-independent acoustic modeling

Gerosa

Giuliani

Brugnara

2009

Speech Communication

View full text Add to dashboard Cite

In automatic speech recognition applications, due to significant differences in voice characteristics, adults and children are usually treated as two population groups, for which different acoustic models are trained. In this paper, age-independent acoustic modeling is investigated in the context of large vocabulary speech recognition. Exploiting a small amount (9 hours) of children's speech and a more significant amount (57 hours) of adult speech, age-independent acoustic models are trained using several methods for speaker adaptive acoustic modeling. Recognition results achieved using these models are compared with those achieved using age-dependent acoustic models for children and adults, respectively. Recognition experiments are performed on four Italian speech corpora, two consisting of children's speech and two of adult speech, using 64k word and 11k word trigram language models. Methods for speaker adaptive acoustic modeling prove to be effective for training ageindependent acoustic models ensuring recognition results at least as good as those achieved with age-dependent acoustic models for adults and children.

show abstract

Towards speech rate independence in large vocabulary continuous speech recognition

Cited by 27 publications

References 6 publications

Robust Speech Rate Estimation for Spontaneous Speech

Robust Speech Rate Estimation for Spontaneous Speech

Automatic speech recognition and speech variability: A review

Towards age-independent acoustic modeling

Contact Info

Product

Resources

About