Related papers: Streaming Non-Autoregressive Model for Accent Conv…

The training of automatic speech recognition (ASR) with little to no supervised data remains an open question. In this work, we demonstrate that streaming Transformer-Transducer (TT) models can be trained from scratch in consumer and…

Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices…

Automatic accent identification (AID) remains a challenging task due to the complex variability of accents, the entanglement of accent cues with speaker traits, and the scarcity of reliable accentlabelled data. To address these challenges,…

In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM…

StreamVoice has recently pushed the boundaries of zero-shot voice conversion (VC) in the streaming domain. It uses a streamable language model (LM) with a context-aware approach to convert semantic features from automatic speech recognition…

Although diffusion-based, non-autoregressive text-to-speech (TTS) systems have demonstrated impressive zero-shot synthesis capabilities, their efficacy is still hindered by two key challenges: the difficulty of text-speech alignment…

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory…

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first…

We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR) and speaker embedding, obtained from a speaker…

Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we investigate the potential…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

We present a fully on-device streaming Speech2Speech conversion model that normalizes a given input speech directly to synthesized output speech. Deploying such a model on mobile devices pose significant challenges in terms of memory…

Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…