Audio-driven talking face has attracted broad interest from academia and industry recently. However, data acquisition and labeling in audio-driven talking face are labor-intensive and costly. The lack of data resource results in poor synthesis effect. To alleviate this issue, we propose to use TTS (Text-To-Speech) for data augmentation to improve few-shot ability of the talking face system. The misalignment problem brought by the TTS audio is solved with the introduction of soft-DTW, which is first adopted in the talking face task. Moreover, features extracted by HuBERT are explored to utilize underlying information of audio, and found to be superior over other features. The proposed method achieves 17%, 14%, 38% dominance on MSE score, DTW score and user study preference repectively over the baseline model, which shows the effectiveness of improving few-shot learning for talking face system with TTS augmentation.
As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker. Its main challenge lies in how to properly extract and leverage the speaker cue to benefit the extracted speech quality. The cue extraction method adopted in majority existing TSE studies is to directly utilize discriminative speaker embedding, which is extracted from the pre-trained models for speaker verification. Although the high speaker discriminability is a most desirable property for speaker verification task, we argue that it may be too sophisticated for TSE. In this study, we propose that a simplified speaker cue with clear class separability might be preferred for TSE. To verify our proposal, we introduce several forms of speaker cues, including naive speaker embedding (such as, x-vector and xi-vector) and new speaker embeddings produced from sparse LDA-transform. Corresponding TSE models are built by integrating these speaker cues with SepFormer (one SOTA speech separation model). Performances of these TSE models are examined on the benchmark WSJ0-2mix dataset. Experimental results validate the effectiveness and generalizability of our proposal, showing up to 9.9% relative improvement in SI-SDRi. Moreover, with SI-SDRi of 19.4 dB and PESQ of 3.78, our best TSE system significantly outperforms the current SOTA systems and offers the top TSE results reported till date on the WSJ0-2mix.
This study investigates the use of Visually Grounded Speech (VGS) models for keyword localisation in speech. The study focusses on two main research questions: (1) Is keyword localisation possible with VGS models and (2) Can keyword localisation be done cross-lingually in a real low-resource setting? Four methods for localisation are proposed and evaluated on an English dataset, with the best-performing method achieving an accuracy of 57%. A new dataset containing spoken captions in Yoruba language is also collected and released for cross-lingual keyword localisation. The cross-lingual model obtains a precision of 16% in actual keyword localisation and this performance can be improved by initialising from a model pretrained on English data. The study presents a detailed analysis of the model's success and failure modes and highlights the challenges of using VGS models for keyword localisation in low-resource settings.
Neural-based text-to-speech (TTS) systems achieve very high-fidelity speech generation because of the rapid neural network developments. However, the huge labeled corpus and high computation cost requirements limit the possibility of developing a high-fidelity TTS system by small companies or individuals. On the other hand, a neural vocoder, which has been widely adopted for the speech generation in neural-based TTS systems, can be trained with a relatively small unlabeled corpus. Therefore, in this paper, we explore a general framework to develop a neural post-filter (NPF) for low-cost TTS systems using neural vocoders. A cyclical approach is proposed to tackle the acoustic and temporal mismatches (AM and TM) of developing an NPF. Both objective and subjective evaluations have been conducted to demonstrate the AM and TM problems and the effectiveness of the proposed framework.
Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the applications requiring both of them. Existing methods usually suffer from some limitations, which rely on either both singing and speaking data from the same person or cascaded models of multiple tasks. To address these problems, a simplified elegant framework for TTS and SVS, named UniSyn, is proposed in this paper. It is an end-to-end unified model that can make a voice speak and sing with only singing or speaking data from this person. To be specific, a multi-conditional variational autoencoder (MC-VAE), which constructs two independent latent sub-spaces with the speaker- and style-related (i.e. speak or sing) conditions for flexible control, is proposed in UniSyn. Moreover, supervised guided-VAE and timbre perturbation with the Wasserstein distance constraint are leveraged to further disentangle the speaker timbre and style. Experiments conducted on two speakers and two singers demonstrate that UniSyn can generate natural speaking and singing voice without corresponding training data. The proposed approach outperforms the state-of-the-art end-to-end voice generation work, which proves the effectiveness and advantages of UniSyn.
We address the problem of human-in-the-loop control for generating highly-structured data. This task is challenging because existing generative models lack an efficient interface through which users can modify the output. Users have the option to either manually explore a non-interpretable latent space, or to laboriously annotate the data with conditioning labels. To solve this, we introduce a novel framework whereby an encoder maps a sparse, human interpretable control space onto the latent space of a generative model. We apply this framework to the task of controlling prosody in text-to-speech synthesis. We propose a model, called Multiple-Instance CVAE (MICVAE), that is specifically designed to encode sparse prosodic features and output complete waveforms. We show empirically that MICVAE displays desirable qualities of a sparse human-in-the-loop control mechanism: efficiency, robustness, and faithfulness. With even a very small number of input values (~4), MICVAE enables users to improve the quality of the output significantly, in terms of listener preference (4:1).
Quantum devices with low qubits are common in the Noisy Intermediate-Scale Quantum (NISQ) era. However, Quantum Neural Network (QNN) running on low-qubit quantum devices would be difficult since it is based on Variational Quantum Circuit (VQC), which requires many qubits. Therefore, it is critical to make QNN with VQC run on low-qubit quantum devices. In this study, we propose a novel VQC called the low-qubit VQC. VQC requires numerous qubits based on the input dimension; however, the low-qubit VQC with linear transformation can liberate this condition. Thus, it allows the QNN to run on low-qubit quantum devices for speech applications. Furthermore, as compared to the VQC, our proposed low-qubit VQC can stabilize the training process more. Based on the low-qubit VQC, we implement QSpeech, a library for quick prototyping of hybrid quantum-classical neural networks in the speech field. It has numerous quantum neural layers and QNN models for speech applications. Experiments on Speech Command Recognition and Text-to-Speech show that our proposed low-qubit VQC outperforms VQC and is more stable.
Transformer models have achieved profound success in prediction tasks in a wide range of applications in natural language processing, speech recognition and computer vision. Extending Transformer's success to safety-critical domains requires calibrated uncertainty estimation which remains under-explored. To address this, we propose Sparse Gaussian Process attention (SGPA), which performs Bayesian inference directly in the output space of multi-head attention blocks (MHAs) in transformer to calibrate its uncertainty. It replaces the scaled dot-product operation with a valid symmetric kernel and uses sparse Gaussian processes (SGP) techniques to approximate the posterior processes of MHA outputs. Empirically, on a suite of prediction tasks on text, images and graphs, SGPA-based Transformers achieve competitive predictive accuracy, while noticeably improving both in-distribution calibration and out-of-distribution robustness and detection.
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance and also the pre-training efficiency, either through decoding with a hybrid ASR system to generate phoneme-level alignments (named PBERT), or performing clustering on the supervised speech features extracted from an end-to-end CTC model (named CTC clustering). Both the hybrid and CTC models are trained on the same small amount of labeled speech as used in fine-tuning. Experiments demonstrate significant superiority of our methods to various SSL and self-training baselines, with up to 17.0% relative WER reduction. Our pre-trained models also show good transferability in a non-ASR speech task.
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual contextual speech embedding at the resolution of an acoustic frame (10-20ms), this work focuses on learning multimodal (speech-text) multilingual speech embedding at the resolution of a sentence (5-10s) such that the embedding vector space is semantically aligned across different languages. We combine state-of-the-art multilingual acoustic frame-level speech representation learning model XLS-R with the Language Agnostic BERT Sentence Embedding (LaBSE) model to create an utterance-level multimodal multilingual speech encoder SAMU-XLSR. Although we train SAMU-XLSR with only multilingual transcribed speech data, cross-lingual speech-text and speech-speech associations emerge in its learned representation space. To substantiate our claims, we use SAMU-XLSR speech encoder in combination with a pre-trained LaBSE text sentence encoder for cross-lingual speech-to-text translation retrieval, and SAMU-XLSR alone for cross-lingual speech-to-speech translation retrieval. We highlight these applications by performing several cross-lingual text and speech translation retrieval tasks across several datasets.