Related papers: Encoder-Decoder Based Attractors for End-to-End Ne…

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin…

Speech foundation models have shown strong transferability across a wide range of speech applications. However, their robustness to age-related domain shift in speaker diarization remains underexplored. In this work, we present a…

This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for…

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Target speaker extraction (TSE) aims to extract the target speaker's voice from the input mixture. Previous studies have concentrated on high-overlapping scenarios. However, real-world applications usually meet more complex scenarios like…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…

This paper proposes a human-in-the-loop speaker-adaptation method for multi-speaker text-to-speech. With a conventional speaker-adaptation method, a target speaker's embedding vector is extracted from his/her reference speech using a…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance…

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text…

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…