Related papers: Decoding the decoder: Contextual sequence-to-seque…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

In this paper, we propose a model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart. Our models are capable of extracting features that take into account both short and long-term…

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for both Switchboard 300…

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Despite the ubiquity of mobile and wearable text messaging applications, the problem of keyboard text decoding is not tackled sufficiently in the light of the enormous success of the deep learning Recurrent Neural Network (RNN) and…

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples…

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units.…

Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models,…

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Thanks to the rise of deep learning and the availability of large-scale audio-visual databases, recent advances have been achieved in Visual Speech Recognition (VSR). Similar to other speech processing tasks, these end-to-end VSR systems…

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…

Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…