相关论文: WavThruVec: Latent speech representation as interm…

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle…

Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

Emotion recognition datasets are relatively small, making the use of the more sophisticated deep learning approaches challenging. In this work, we propose a transfer learning method for speech emotion recognition where features extracted…

In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

This paper proposes a novel Sequence-to-Sequence (Seq2Seq) model integrating the structure of Hidden Semi-Markov Models (HSMMs) into its attention mechanism. In speech synthesis, it has been shown that methods based on Seq2Seq models using…

Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are…

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challenges. Typically,…

Wav2vec 2.0 (W2V2) has shown strong performance in pathological speech analysis by effectively capturing the characteristics of atypical speech. Despite its success, it remains unclear which components of its learned representations are…

In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to…

Learning music representations that are general-purpose offers the flexibility to finetune several downstream tasks using smaller datasets. The wav2vec 2.0 speech representation model showed promising results in many downstream speech…

While Word2Vec represents words (in text) as vectors carrying semantic information, audio Word2Vec was shown to be able to represent signal segments of spoken words as vectors carrying phonetic structure information. Audio Word2Vec can be…

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

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…