相关论文: Bytes are All You Need: End-to-End Multilingual Sp…

Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to representing at most full words. The BoundlessBPE and SuperBPE algorithms extend…

In this paper, we present Synergy, a language model that bridges different levels of abstraction in an end-to-end fashion through a learned routing mechanism. Focusing on low-level linguistic abstraction, we trained our model as a…

In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs).…

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Our model is based on VITS, a high-quality end-to-end text-to-speech model, but adopts two changes for more…

While Large Language Models (LLMs) have shown potential in speech generation and recognition, their applications are mainly confined to monolingual scenarios, with limited explorations in code-switched (CS) contexts. In this paper, we…

A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts. Although contemporary text encoding methods cover most of the world's writing systems, they exhibit bias…

End-to-end (E2E) modeling is advantageous for automatic speech recognition (ASR) especially for Japanese since word-based tokenization of Japanese is not trivial, and E2E modeling is able to model character sequences directly. This paper…

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model…

In this paper, we propose a simple yet effective framework for multilingual end-to-end speech translation (ST), in which speech utterances in source languages are directly translated to the desired target languages with a universal…

We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks:…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training time when data is…

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding…

Language-agnostic many-to-one end-to-end speech translation models can convert audio signals from different source languages into text in a target language. These models do not need source language identification, which improves user…

We investigate a novel cross-lingual multi-speaker text-to-speech synthesis approach for generating high-quality native or accented speech for native/foreign seen/unseen speakers in English and Mandarin. The system consists of three…

Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level…

In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration)…