Related papers: DualVC 3: Leveraging Language Model Generated Pseu…

End-to-end Automatic Speech Recognition (ASR) systems are rapidly claiming to become state-of-art over other modeling methods. Several techniques have been introduced to improve their ability to handle multiple languages. However, due to…

This report presents VibeVoice-ASR, a general-purpose speech understanding framework built upon VibeVoice, designed to address the persistent challenges of context fragmentation and multi-speaker complexity in long-form audio (e.g.,…

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…

During conversations, humans are capable of inferring the intention of the speaker at any point of the speech to prepare the following action promptly. Such ability is also the key for conversational systems to achieve rhythmic and natural…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more…

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates…

End-2-end (E2E) models have become increasingly popular in some ASR tasks because of their performance and advantages. These E2E models directly approximate the posterior distribution of tokens given the acoustic inputs. Consequently, the…

In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial…

Style voice conversion aims to transform the speaking style of source speech into a desired style while keeping the original speaker's identity. However, previous style voice conversion approaches primarily focus on well-defined domains…

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…

Zero-shot voice conversion is becoming an increasingly popular research topic, as it promises the ability to transform speech to sound like any speaker. However, relatively little work has been done on end-to-end methods for this task,…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…