A large and growing amount of speech content in real-life scenarios is being recorded on common consumer devices in uncontrolled environments, resulting in degraded speech quality. Transforming such low-quality device-degraded speech into high-quality speech is a goal of speech enhancement (SE). This paper introduces a new speech dataset, DDS, to facilitate the research on SE. DDS provides aligned parallel recordings of high-quality speech (recorded in professional studios) and a number of versions of low-quality speech, producing approximately 2,000 hours speech data. The DDS dataset covers 27 realistic recording conditions by combining diverse acoustic environments and microphone devices, and each version of a condition consists of multiple recordings from six different microphone positions to simulate various signal-to-noise ratio (SNR) and reverberation levels. We also test several SE baseline systems on the DDS dataset and show the impact of recording diversity on performance.
We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of the translation with the original speech segments, neural text-to-speech with fine tuning of the duration of each utterance, and, finally, audio rendering to enriches text-to-speech output with background noise and reverberation extracted from the original audio. We report on a subjective evaluation of automatic dubbing of excerpts of TED Talks from English into Italian, which measures the perceived naturalness of automatic dubbing and the relative importance of each proposed enhancement.
We introduce CVSS, a massively multilingual-to-English speech-to-speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems. Two versions of translation speeches are provided: 1) CVSS-C: All the translation speeches are in a single high-quality canonical voice; 2) CVSS-T: The translation speeches are in voices transferred from the corresponding source speeches. In addition, CVSS provides normalized translation text which matches the pronunciation in the translation speech. On each version of CVSS, we built baseline multilingual direct S2ST models and cascade S2ST models, verifying the effectiveness of the corpus. To build strong cascade S2ST baselines, we trained an ST model on CoVoST 2, which outperforms the previous state-of-the-art trained on the corpus without extra data by 5.8 BLEU. Nevertheless, the performance of the direct S2ST models approaches the strong cascade baselines when trained from scratch, and with only 0.1 or 0.7 BLEU difference on ASR transcribed translation when initialized from matching ST models.
An unsupervised text-to-speech synthesis (TTS) system learns to generate the speech waveform corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech. Developing such a system can significantly improve the availability of speech technology to languages without a large amount of parallel speech and text data. This paper proposes an unsupervised TTS system by leveraging recent advances in unsupervised automatic speech recognition (ASR). Our unsupervised system can achieve comparable performance to the supervised system in seven languages with about 10-20 hours of speech each. A careful study on the effect of text units and vocoders has also been conducted to better understand what factors may affect unsupervised TTS performance. The samples generated by our models can be found at https://cactuswiththoughts.github.io/UnsupTTS-Demo.
As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech detection. By attempting to replicate a hate speech detection experiment performed on an existing Twitter corpus annotated for hate speech, we highlight some issues that arise from doing research in the field of hate speech, which is essentially still in its infancy. We take a critical look at the training corpus in order to understand its biases, while also using it to venture beyond hate speech detection and investigate whether it can be used to shed light on other facets of research, such as popularity of hate tweets.
The acoustic and linguistic features of preschool speech are investigated in this study to design an automated speech recognition (ASR) system. Acoustic fluctuation has been highlighted as a significant barrier to developing high-performance ASR applications for youngsters. Because of the epidemic, preschool speech assessment should be conducted online. Accordingly, there is a need for an automatic speech recognition system. We were confronted with new challenges in our cognitive system, including converting meaningless words from speech to text and recognizing word sequence. After testing and experimenting with several models we obtained a 3.1\% phoneme error rate in Persian. Wav2Vec 2.0 is a paradigm that could be used to build a robust end-to-end speech recognition system.
In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components. Typically, the speech signal is considered stationary within fixed segments of 20-40 ms, but the degree of stationarity varies over time. For decomposing noisy speech into its voiced and unvoiced components, a fixed segmentation may be too crude, and we here propose to adapt the segment length according to the signal local characteristics. The segmentation relies on parameter estimates of a hybrid speech model and the maximum a posteriori (MAP) and log-likelihood criteria as rules for model selection among the possible segment lengths, for voiced and unvoiced speech, respectively. Given the optimal segmentation markers and the estimated statistics, both components are estimated using linear filtering. A codebook-based approach differentiates between unvoiced speech and noise. A better extraction of the components is possible by taking into account the adaptive segmentation, compared to a fixed one. Also, a lower distortion for voiced speech and higher segSNR for both components is possible, as compared to other decomposition methods.