Dysarthria speech contains the pathological characteristics of vocal tract and vocal fold, but so far, they have not yet been included in traditional acoustic feature sets. Moreover, the nonlinearity and non-stationarity of speech have been ignored. In this paper, we propose a feature enhancement algorithm for dysarthria speech called WHFEMD. It combines empirical mode decomposition (EMD) and fast Walsh-Hadamard transform (FWHT) to enhance features. With the proposed algorithm, the fast Fourier transform of the dysarthria speech is first performed and then followed by EMD to get intrinsic mode functions (IMFs). After that, FWHT is used to output new coefficients and to extract statistical features based on IMFs, power spectral density, and enhanced gammatone frequency cepstral coefficients. To evaluate the proposed approach, we conducted experiments on two public pathological speech databases including UA Speech and TORGO. The results show that our algorithm performed better than traditional features in classification. We achieved improvements of 13.8% (UA Speech) and 3.84% (TORGO), respectively. Furthermore, the incorporation of an imbalanced classification algorithm to address data imbalance has resulted in a 12.18% increase in recognition accuracy. This algorithm effectively addresses the challenges of the imbalanced dataset and non-linearity in dysarthric speech and simultaneously provides a robust representation of the local pathological features of the vocal folds and tracts.
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental assumption. In this paper, we propose a unified multichannel far-field speech recognition system that combines the neural beamforming and transformer-based Listen, Spell, Attend (LAS) speech recognition system, which extends the end-to-end speech recognition system further to include speech enhancement. Such framework is then jointly trained to optimize the final objective of interest. Specifically, factored complex linear projection (fCLP) has been adopted to form the neural beamforming. Several pooling strategies to combine look directions are then compared in order to find the optimal approach. Moreover, information of the source direction is also integrated in the beamforming to explore the usefulness of source direction as a prior, which is usually available especially in multi-modality scenario. Experiments on different microphone array geometry are conducted to evaluate the robustness against spacing variance of microphone array. Large in-house databases are used to evaluate the effectiveness of the proposed framework and the proposed method achieve 19.26\% improvement when compared with a strong baseline.
Although numerous recent studies have suggested new frameworks for zero-shot TTS using large-scale, real-world data, studies that focus on the intelligibility of zero-shot TTS are relatively scarce. Zero-shot TTS demands additional efforts to ensure clear pronunciation and speech quality due to its inherent requirement of replacing a core parameter (speaker embedding or acoustic prompt) with a new one at the inference stage. In this study, we propose a zero-shot TTS model focused on intelligibility, which we refer to as Intelli-Z. Intelli-Z learns speaker embeddings by using multi-speaker TTS as its teacher and is trained with a cycle-consistency loss to include mismatched text-speech pairs for training. Additionally, it selectively aggregates speaker embeddings along the temporal dimension to minimize the interference of the text content of reference speech at the inference stage. We substantiate the effectiveness of the proposed methods with an ablation study. The Mean Opinion Score (MOS) increases by 9% for unseen speakers when the first two methods are applied, and it further improves by 16% when selective temporal aggregation is applied.
Music auto-tagging is crucial for enhancing music discovery and recommendation. Existing models in Music Information Retrieval (MIR) struggle with real-world noise such as environmental and speech sounds in multimedia content. This study proposes a method inspired by speech-related tasks to enhance music auto-tagging performance in noisy settings. The approach integrates Domain Adversarial Training (DAT) into the music domain, enabling robust music representations that withstand noise. Unlike previous research, this approach involves an additional pretraining phase for the domain classifier, to avoid performance degradation in the subsequent phase. Adding various synthesized noisy music data improves the model's generalization across different noise levels. The proposed architecture demonstrates enhanced performance in music auto-tagging by effectively utilizing unlabeled noisy music data. Additional experiments with supplementary unlabeled data further improves the model's performance, underscoring its robust generalization capabilities and broad applicability.
Spoken Question Answering (SQA) is essential for machines to reply to user's question by finding the answer span within a given spoken passage. SQA has been previously achieved without ASR to avoid recognition errors and Out-of-Vocabulary (OOV) problems. However, the real-world problem of Open-domain SQA (openSQA), in which the machine needs to first retrieve passages that possibly contain the answer from a spoken archive in addition, was never considered. This paper proposes the first known end-to-end framework, Speech Dense Passage Retriever (SpeechDPR), for the retrieval component of the openSQA problem. SpeechDPR learns a sentence-level semantic representation by distilling knowledge from the cascading model of unsupervised ASR (UASR) and text dense retriever (TDR). No manually transcribed speech data is needed. Initial experiments showed performance comparable to the cascading model of UASR and TDR, and significantly better when UASR was poor, verifying this approach is more robust to speech recognition errors.
Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice. We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion. In training data selection, we demonstrate that MOS enables effective filtering of samples from unbalanced datasets. In the model fusion, our results demonstrate that incorporating MOS as a gating mechanism in FAD model fusion enhances overall performance.
We introduce an adaptive scheduling for adaptive sampling as a novel way of machine learning in the construction of part-of-speech taggers. The goal is to speed up the training on large data sets, without significant loss of performance with regard to an optimal configuration. In contrast to previous methods using a random, fixed or regularly rising spacing between the instances, ours analyzes the shape of the learning curve geometrically in conjunction with a functional model to increase or decrease it at any time. The algorithm proves to be formally correct regarding our working hypotheses. Namely, given a case, the following one is the nearest ensuring a net gain of learning ability from the former, it being possible to modulate the level of requirement for this condition. We also improve the robustness of sampling by paying greater attention to those regions of the training data base subject to a temporary inflation in performance, thus preventing the learning from stopping prematurely. The proposal has been evaluated on the basis of its reliability to identify the convergence of models, corroborating our expectations. While a concrete halting condition is used for testing, users can choose any condition whatsoever to suit their own specific needs.
This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multi-scale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR model adopts an end-to-end architecture with joint CTC/attention loss, comprising a ResNet3D visual frontend, an E-Branchformer encoder, and a Transformer decoder. Experiments show that our system achieves 34.76% CER for the Single-Speaker Task and 41.06% CER for the Multi-Speaker Task after multi-system fusion, ranking first place in all three tracks we participate.
Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. In most cases, TTS systems are built using a single speaker's voice. However, there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper is the first to incorporate the representations from text-based and speech-based self-supervised learning models into multilingual speech synthesis tasks. We conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has been proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetical low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.
Automatic recognition of dysarthric speech remains a highly challenging task to date. Neuro-motor conditions and co-occurring physical disabilities create difficulty in large-scale data collection for ASR system development. Adapting SSL pre-trained ASR models to limited dysarthric speech via data-intensive parameter fine-tuning leads to poor generalization. To this end, this paper presents an extensive comparative study of various data augmentation approaches to improve the robustness of pre-trained ASR model fine-tuning to dysarthric speech. These include: a) conventional speaker-independent perturbation of impaired speech; b) speaker-dependent speed perturbation, or GAN-based adversarial perturbation of normal, control speech based on their time alignment against parallel dysarthric speech; c) novel Spectral basis GAN-based adversarial data augmentation operating on non-parallel data. Experiments conducted on the UASpeech corpus suggest GAN-based data augmentation consistently outperforms fine-tuned Wav2vec2.0 and HuBERT models using no data augmentation and speed perturbation across different data expansion operating points by statistically significant word error rate (WER) reductions up to 2.01% and 0.96% absolute (9.03% and 4.63% relative) respectively on the UASpeech test set of 16 dysarthric speakers. After cross-system outputs rescoring, the best system produced the lowest published WER of 16.53% (46.47% on very low intelligibility) on UASpeech.