相关论文: Sequence-to-Sequence Voice Reconstruction for Sile…

Voice conversion (VC) is a task to transform a person's voice to different style while conserving linguistic contents. Previous state-of-the-art on VC is based on sequence-to-sequence (seq2seq) model, which could mislead linguistic…

Speech sound disorder (SSD) refers to the developmental disorder in which children encounter persistent difficulties in correctly pronouncing words. Assessment of SSD has been relying largely on trained speech and language pathologists…

Objective. In this article, we present data and methods for decoding speech articulations using surface electromyogram (EMG) signals. EMG-based speech neuroprostheses offer a promising approach for restoring audible speech in individuals…

Attention-based sequence-to-sequence (seq2seq) speech synthesis has achieved extraordinary performance. But a studio-quality corpus with manual transcription is necessary to train such seq2seq systems. In this paper, we propose an approach…

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…

We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data. Trained on the…

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way…

For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone…

This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by…

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…

While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…

In this paper, we present an improved model for voicing silent speech, where audio is synthesized from facial electromyography (EMG) signals. To give our model greater flexibility to learn its own input features, we directly use EMG signals…

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of…

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…