Related papers: Do End-to-End Neural Diarization Attractors Need t…

In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an…

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of…

The ideal goal of voice conversion is to convert the source speaker's speech to sound naturally like the target speaker while maintaining the linguistic content and the prosody of the source speech. However, current approaches are…

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate…

While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Entity disambiguation (ED) is the task of linking mentions in text to corresponding entries in a knowledge base. Dual Encoders address this by embedding mentions and label candidates in a shared embedding space and applying a similarity…

The joint training of speech enhancement and speaker embedding networks for speaker recognition is widely adopted under noisy acoustic environments. While effective, this paradigm often fails to leverage the generalization and robustness…

Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and…

In this work, we present an end-to-end binaural speech synthesis system that combines a low-bitrate audio codec with a powerful binaural decoder that is capable of accurate speech binauralization while faithfully reconstructing…

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Differing from prior work that solely relies on the content of conversation history to generate a…

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

In this paper we demonstrate that performance of a speaker verification system can be improved by concatenating electroencephalography (EEG) signal features with speech signal features or only using EEG signal features. We use…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in…

Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…

Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs…