The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition

Prananta, Luke; Halpern, Bence Mark; Feng, Siyuan; Scharenborg, Odette

doi:10.48550/arxiv.2201.04908

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These works, however, require parallel data during training or known speaker identities during test time. In [16] it was shown that speech recognition for dysarthric speech can be enhanced by a simple linear interpolation of an utterance's spectrogram and outperforms cycle-based VC approaches on parallel data.…”

Section: Introductionmentioning

confidence: 99%

Investigation into Target Speaking Rate Adaptation for Voice Conversion

Kuhlmann¹,

Seebauer²,

Ebbers³

et al. 2022

Interspeech 2022

View full text Add to dashboard Cite

Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained with non-parallel and unlabeled speech data. However, previous approaches perform disentanglement only implicitly via some sort of information bottleneck or normalization, where it is usually hard to find a good trade-off between voice conversion and content reconstruction. Further, previous works usually do not consider an adaptation of the speaking rate to the target speaker or they put some major restrictions to the data or use case. Therefore, the contribution of this work is two-fold. First, we employ an explicit and fully unsupervised disentanglement approach, which has previously only been used for representation learning, and show that it allows to obtain both superior voice conversion and content reconstruction. Second, we investigate simple and generic approaches to linearly adapt the length of a speech signal, and hence the speaking rate, to a target speaker and show that the proposed adaptation allows to increase the speaking rate similarity with respect to the target speaker.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation into Target Speaking Rate Adaptation for Voice Conversion

Kuhlmann¹,

Seebauer²,

Ebbers³

et al. 2022

Interspeech 2022

View full text Add to dashboard Cite

show abstract

“…Cycle-consistent and adversarial loss are utilized to train CycleGAN without requiring paired data. It has been applied to many unsupervised domain adaptation tasks, including voice conversion [23][24][25]. In addition to these DNNbased conversion models, traditional signal processing methods, e.g., formant modification [26] and time-scale modification [10], can also be applied to acoustic feature conversion.…”

Section: Introductionmentioning

confidence: 99%

An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech

Liu¹,

Li²,

Lee³

2022

Preprint

View full text Add to dashboard Cite

The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR) system trained on adult speech to child speech directly, as a result of domain mismatch. The present study is focused on adult-to-child acoustic feature conversion to alleviate this mismatch. Different acoustic feature conversion approaches, including deep neural network based and signal processing based, are investigated and compared under a fair experimental setting, in which converted acoustic features from the same amount of labeled adult speech are used to train the ASR models from scratch. Experimental results reveal that not all of the conversion methods lead to ASR performance gain. Specifically, as a classic unsupervised domain adaptation method, the statistic matching does not show an effectiveness. A disentanglementbased auto-encoder (DAE) conversion framework is found to be useful and the approach of F0 normalization achieves the best performance. It is noted that the F0 distribution of converted features is an important attribute to reflect the conversion quality, while utilizing an adult-child deep classification model to make judgment is shown to be inappropriate.

show abstract

The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition

Cited by 2 publications

References 16 publications

Investigation into Target Speaking Rate Adaptation for Voice Conversion

Investigation into Target Speaking Rate Adaptation for Voice Conversion

An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech

Contact Info

Product

Resources

About