Related papers: Streaming Parrotron for on-device speech-to-speech…

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Current end-to-end autoregressive TTS systems (e.g. Tacotron 2) have outperformed traditional parallel approaches on the quality of synthesized speech. However, they introduce new problems at the same time. Due to the autoregressive nature,…

In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics. We achieve this by…

Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficiency. Additionally,…

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…

In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to…

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal…

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder…

Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade systems, which are often composed of recognition, translation…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Binaural rendering aims to synthesize binaural audio that mimics natural hearing based on a mono audio and the locations of the speaker and listener. Although many methods have been proposed to solve this problem, they struggle with…

Lip-to-speech (L2S) synthesis, which reconstructs speech from visual cues, faces challenges in accuracy and naturalness due to limited supervision in capturing linguistic content, accents, and prosody. In this paper, we propose RESOUND, a…

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic…

In this paper, we introduce our work of building a Streaming Multilingual Speech Model (SM2), which can transcribe or translate multiple spoken languages into texts of the target language. The backbone of SM2 is Transformer Transducer,…

We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer…

This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize ``who spoke what'' with low latency even when multiple people are speaking simultaneously. Our model is based on token-level…

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…