Related papers: Rhythm-controllable Attention with High Robustness…
The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenges in the next-token prediction posed by lengthy sequences of…
Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…
Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural…
Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to verbosity. We propose Multiround Adaptive Chain-of-Thought Compression (MACC), a framework that leverages the token…
This paper proposes a non-autoregressive extension of our previously proposed sequence-to-sequence (S2S) model-based voice conversion (VC) methods. S2S model-based VC methods have attracted particular attention in recent years for their…
Recently, synthesizing personalized speech by text-to-speech (TTS) application is highly demanded. But the previous TTS models require a mass of target speaker speeches for training. It is a high-cost task, and hard to record lots of…
Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on…
Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs. However, existing deep learning methods for RUL prediction…
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…
The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…
Recent studies have outlined the accessibility challenges faced by blind or visually impaired, and less-literate people, in interacting with social networks, in-spite of facilitating technologies such as monotone text-to-speech (TTS) screen…
Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed…
End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. And the synthesised speech may also suffer from some error…
Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…
Speech synthesis technology has witnessed significant advancements in recent years, enabling the creation of natural and expressive synthetic speech. One area of particular interest is the generation of synthetic child speech, which…
The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…
The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…
In this project, we aim to build a Text-to-Speech system able to produce speech with a controllable emotional expressiveness. We propose a methodology for solving this problem in three main steps. The first is the collection of emotional…