相关论文: On a Novel Speech Representation Using Multitapere…

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS)…

In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…

The control of perceptual voice qualities in a text-to-speech (TTS) system is of interest for applications where unmanipu- lated and manipulated speech probes can serve to illustrate pho- netic concepts that are otherwise difficult to…

Movable antenna (MA) has emerged as a promising technology to enhance wireless communication performance by enabling the local movement of antennas at the transmitter (Tx) and/or receiver (Rx) for achieving more favorable channel…

We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on…

Deep generative models for Speech Enhancement (SE) received increasing attention in recent years. The most prominent example are Generative Adversarial Networks (GANs), while normalizing flows (NF) received less attention despite their…

The goal of this work is to simultaneously generate natural talking faces and speech outputs from text. We achieve this by integrating Talking Face Generation (TFG) and Text-to-Speech (TTS) systems into a unified framework. We address the…

This work focuses on full-body co-speech gesture generation. Existing methods typically employ an autoregressive model accompanied by vector-quantized tokens for gesture generation, which results in information loss and compromises the…

In this paper, we study articulatory synthesis, a speech synthesis method using human vocal tract information that offers a way to develop efficient, generalizable and interpretable synthesizers. While recent advances have enabled…

Previous studies have proven that integrating video signals, as a complementary modality, can facilitate improved performance for speech enhancement (SE). However, video clips usually contain large amounts of data and pose a high cost in…

Multichannel processing is widely used for speech enhancement but several limitations appear when trying to deploy these solutions to the real-world. Distributed sensor arrays that consider several devices with a few microphones is a viable…

Morphosyntactic lexicons and word vector representations have both proven useful for improving the accuracy of statistical part-of-speech taggers. Here we compare the performances of four systems on datasets covering 16 languages, two of…

We describe a modulation-domain loss function for deep-learning-based speech enhancement systems. Learnable spectro-temporal receptive fields (STRFs) were adapted to optimize for a speaker identification task. The learned STRFs were then…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

With read-aloud speech synthesis achieving high naturalness scores, there is a growing research interest in synthesising spontaneous speech. However, human spontaneous face-to-face conversation has both spoken and non-verbal aspects (here,…

Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors…

In this paper, we study different approaches for classifying emotions from speech using acoustic and text-based features. We propose to obtain contextualized word embeddings with BERT to represent the information contained in speech…

Multimodal learning has been proven to be an effective method to improve speech enhancement (SE) performance, especially in challenging situations such as low signal-to-noise ratios, speech noise, or unseen noise types. In previous studies,…

Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech recognition in noisy environments. However, in the context of ad-hoc microphone…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…