This paper introduces RyanSpeech, a new speech corpus for research on automated text-to-speech (TTS) systems. Publicly available TTS corpora are often noisy, recorded with multiple speakers, or lack quality male speech data. In order to meet the need for a high quality, publicly available male speech corpus within the field of speech recognition, we have designed and created RyanSpeech which contains textual materials from real-world conversational settings. These materials contain over 10 hours of a professional male voice actor's speech recorded at 44.1 kHz. This corpus's design and pipeline make RyanSpeech ideal for developing TTS systems in real-world applications. To provide a baseline for future research, protocols, and benchmarks, we trained 4 state-of-the-art speech models and a vocoder on RyanSpeech. The results show 3.36 in mean opinion scores (MOS) in our best model. We have made both the corpus and trained models for public use.
In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech. Despite long-lasting efforts to build speaker- and text-independent ASR systems for people with dysarthria, the performance of state-of-the-art systems is still considerably lower on this type of speech than on normal speech. The most prominent reason for the inferior performance is the high variability in pathological speech that is characterized by the spectrotemporal deviations caused by articulatory impairments due to various etiologies. To cope with this high variation, we propose to use speech representations which utilize articulatory information together with the acoustic properties. A designated acoustic model, namely a fused-feature-map convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time convolution on articulatory features is trained and tested on a Dutch and a Flemish pathological speech corpus. The ASR performance of fCNN-based ASR system using joint features is compared to other neural network architectures such conventional CNNs and time-frequency convolutional networks (TFCNNs) in several training scenarios.
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extractor using nine Southern Bantu languages that form part of the freely available multilingual NCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features and i-vectors to train acoustic models for automatic speech recognition (ASR) in the target code-switched languages. Our results show that the inclusion of the mBNF features leads to clear performance improvements over a baseline trained without the mBNFs for code-switched English-isiZulu, English-isiXhosa, English-Sesotho and English-Setswana speech.
The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and soft speech units as input features. We find that discrete representations effectively remove speaker information but discard some linguistic content - leading to mispronunciations. As a solution, we propose soft speech units. To learn soft units, we predict a distribution over discrete speech units. By modeling uncertainty, soft units capture more content information, improving the intelligibility and naturalness of converted speech. Samples available at https://ubisoft-laforge.github.io/speech/soft-vc/
Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretraining from two different modalities: speech and text. The proposed method, tts4pretrain complements the power of contrastive learning in self-supervision with linguistic/lexical representations derived from synthesized speech, effectively learning from untranscribed speech and unspoken text. Lexical learning in the speech encoder is enforced through an additional sequence loss term that is coupled with contrastive loss during pretraining. We demonstrate that this novel pretraining method yields Word Error Rate (WER) reductions of 10% relative on the well-benchmarked, Librispeech task over a state-of-the-art baseline pretrained with wav2vec2.0 only. The proposed method also serves as an effective strategy to compensate for the lack of transcribed speech, effectively matching the performance of 5000 hours of transcribed speech with just 100 hours of transcribed speech on the AMI meeting transcription task. Finally, we demonstrate WER reductions of up to 15% on an in-house Voice Search task over traditional pretraining. Incorporating text into encoder pretraining is complimentary to rescoring with a larger or in-domain language model, resulting in additional 6% relative reduction in WER.
Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the intermediate representation. Although the intermediate representation is served as a bridge, there still exists critical mismatch between the acoustic model and the vocoder as they are commonly separately learned and work on different distributions of representation, leading to inevitable artifacts in the synthesized speech. In this work, different from using pre-designed intermediate representation in most previous studies, we propose to use VAE combining with GAN to learn a latent representation directly from speech and then utilize a flow-based acoustic model to model the distribution of the latent representation from text. In this way, the mismatch problem is migrated as the two stages work on the same distribution. Results demonstrate that the flow-based acoustic model can exactly model the distribution of our learned speech representation and the proposed TTS framework, namely Glow-WaveGAN, can produce high fidelity speech outperforming the state-of-the-art GAN-based model.
In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth information to the model, and bandwidth embeddings are jointly learned as part of acoustic model training. Experimental evaluations show that using bandwidth embeddings helps the model to handle the variability of the narrow and wideband speech, and makes it possible to train a mixed-bandwidth AM. Furthermore, we propose to use parallel convolutional layers to handle the mismatch between the narrow and wideband speech better, where separate convolution layers are used for each type of input speech signal. Our best system achieves 13% relative improvement on narrowband speech, while not degrading on wideband speech.
In this thesis, we present a statistical language model for resolving speech repairs, intonational boundaries and discourse markers. Rather than finding the best word interpretation for an acoustic signal, we redefine the speech recognition problem to so that it also identifies the POS tags, discourse markers, speech repairs and intonational phrase endings (a major cue in determining utterance units). Adding these extra elements to the speech recognition problem actually allows it to better predict the words involved, since we are able to make use of the predictions of boundary tones, discourse markers and speech repairs to better account for what word will occur next. Furthermore, we can take advantage of acoustic information, such as silence information, which tends to co-occur with speech repairs and intonational phrase endings, that current language models can only regard as noise in the acoustic signal. The output of this language model is a much fuller account of the speaker's turn, with part-of-speech assigned to each word, intonation phrase endings and discourse markers identified, and speech repairs detected and corrected. In fact, the identification of the intonational phrase endings, discourse markers, and resolution of the speech repairs allows the speech recognizer to model the speaker's utterances, rather than simply the words involved, and thus it can return a more meaningful analysis of the speaker's turn for later processing.
Most network-based speech recognition methods are based on the assumption that the labels of two adjacent speech samples in the network are likely to be the same. However, assuming the pairwise relationship between speech samples is not complete. The information a group of speech samples that show very similar patterns and tend to have similar labels is missed. The natural way overcoming the information loss of the above assumption is to represent the feature data of speech samples as the hypergraph. Thus, in this paper, the three un-normalized, random walk, and symmetric normalized hypergraph Laplacian based semi-supervised learning methods applied to hypergraph constructed from the feature data of speech samples in order to predict the labels of speech samples are introduced. Experiment results show that the sensitivity performance measures of these three hypergraph Laplacian based semi-supervised learning methods are greater than the sensitivity performance measures of the Hidden Markov Model method (the current state of the art method applied to speech recognition problem) and graph based semi-supervised learning methods (i.e. the current state of the art network-based method for classification problems) applied to network created from the feature data of speech samples.