In multilingual speech recognition systems, a situation can often arise when the language is not known in advance, but the signal has already been received and is being processed. For such cases, some generalized model is needed that will be able to respond to phonetic differences and, depending on them, correctly recog-nize speech in the desired language. To build such a model, it is necessary to set the values of phonetic parameters, and then compare similar sounds, establishing significant differences.
Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional information is distributed across different scales of speech features, e.\,g., word, phrase, and utterance. Drawing above inspiration, this paper presents a hierarchical speech Transformer with shifted windows to aggregate multi-scale emotion features for speech emotion recognition (SER), called Speech Swin-Transformer. Specifically, we first divide the speech spectrogram into segment-level patches in the time domain, composed of multiple frame patches. These segment-level patches are then encoded using a stack of Swin blocks, in which a local window Transformer is utilized to explore local inter-frame emotional information across frame patches of each segment patch. After that, we also design a shifted window Transformer to compensate for patch correlations near the boundaries of segment patches. Finally, we employ a patch merging operation to aggregate segment-level emotional features for hierarchical speech representation by expanding the receptive field of Transformer from frame-level to segment-level. Experimental results demonstrate that our proposed Speech Swin-Transformer outperforms the state-of-the-art methods.
Recent advancements in language models have significantly enhanced performance in multiple speech-related tasks. Existing speech language models typically utilize task-dependent prompt tokens to unify various speech tasks in a single model. However, this design omits the intrinsic connections between different speech tasks, which can potentially boost the performance of each task. In this work, we propose a novel decoder-only speech language model, SpeechComposer, that can unify common speech tasks by composing a fixed set of prompt tokens. Built upon four primary tasks -- speech synthesis, speech recognition, speech language modeling, and text language modeling -- SpeechComposer can easily extend to more speech tasks via compositions of well-designed prompt tokens, like voice conversion and speech enhancement. The unification of prompt tokens also makes it possible for knowledge sharing among different speech tasks in a more structured manner. Experimental results demonstrate that our proposed SpeechComposer can improve the performance of both primary tasks and composite tasks, showing the effectiveness of the shared prompt tokens. Remarkably, the unified decoder-only model achieves a comparable and even better performance than the baselines which are expert models designed for single tasks.
Cross-corpus speech emotion recognition (SER) aims to transfer emotional knowledge from a labeled source corpus to an unlabeled corpus. However, prior methods require access to source data during adaptation, which is unattainable in real-life scenarios due to data privacy protection concerns. This paper tackles a more practical task, namely source-free cross-corpus SER, where a pre-trained source model is adapted to the target domain without access to source data. To address the problem, we propose a novel method called emotion-aware contrastive adaptation network (ECAN). The core idea is to capture local neighborhood information between samples while considering the global class-level adaptation. Specifically, we propose a nearest neighbor contrastive learning to promote local emotion consistency among features of highly similar samples. Furthermore, relying solely on nearest neighborhoods may lead to ambiguous boundaries between clusters. Thus, we incorporate supervised contrastive learning to encourage greater separation between clusters representing different emotions, thereby facilitating improved class-level adaptation. Extensive experiments indicate that our proposed ECAN significantly outperforms state-of-the-art methods under the source-free cross-corpus SER setting on several speech emotion corpora.
Emotional Voice Messages (EMOVOME) is a spontaneous speech dataset containing 999 audio messages from real conversations on a messaging app from 100 Spanish speakers, gender balanced. Voice messages were produced in-the-wild conditions before participants were recruited, avoiding any conscious bias due to laboratory environment. Audios were labeled in valence and arousal dimensions by three non-experts and two experts, which were then combined to obtain a final label per dimension. The experts also provided an extra label corresponding to seven emotion categories. To set a baseline for future investigations using EMOVOME, we implemented emotion recognition models using both speech and audio transcriptions. For speech, we used the standard eGeMAPS feature set and support vector machines, obtaining 49.27% and 44.71% unweighted accuracy for valence and arousal respectively. For text, we fine-tuned a multilingual BERT model and achieved 61.15% and 47.43% unweighted accuracy for valence and arousal respectively. This database will significantly contribute to research on emotion recognition in the wild, while also providing a unique natural and freely accessible resource for Spanish.
In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers. Consequently, when the trained model is confronted with data from new speakers, its performance tends to degrade. To address the issue, we propose a Dynamic Joint Distribution Adaptation (DJDA) method under the framework of multi-source domain adaptation. DJDA firstly utilizes joint distribution adaptation (JDA), involving marginal distribution adaptation (MDA) and conditional distribution adaptation (CDA), to more precisely measure the multi-domain distribution shifts caused by different speakers. This helps eliminate speaker bias in emotion features, allowing for learning discriminative and speaker-invariant speech emotion features from coarse-level to fine-level. Furthermore, we quantify the adaptation contributions of MDA and CDA within JDA by using a dynamic balance factor based on $\mathcal{A}$-Distance, promoting to effectively handle the unknown distributions encountered in data from new speakers. Experimental results demonstrate the superior performance of our DJDA as compared to other state-of-the-art (SOTA) methods.
Speech sound disorder (SSD) is defined as a persistent impairment in speech sound production leading to reduced speech intelligibility and hindered verbal communication. Early recognition and intervention of children with SSD and timely referral to speech and language therapists (SLTs) for treatment are crucial. Automated detection of speech impairment is regarded as an efficient method for examining and screening large populations. This study focuses on advancing the automatic diagnosis of SSD in early childhood by proposing a technical solution that integrates ultrasound tongue imaging (UTI) with deep-learning models. The introduced FusionNet model combines UTI data with the extracted texture features to classify UTI. The overarching aim is to elevate the accuracy and efficiency of UTI analysis, particularly for classifying speech sounds associated with SSD. This study compared the FusionNet approach with standard deep-learning methodologies, highlighting the excellent improvement results of the FusionNet model in UTI classification and the potential of multi-learning in improving UTI classification in speech therapy clinics.
Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the scarcity of labeled multichannel data and complex ambient noises. The efficacy of self-supervised learning for far-field multichannel and multi-modal speech processing has not been well explored. Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs. First, we propose a multi-path structure to process multichannel audio streams and a visual stream in parallel, with intra- and inter-channel contrastive losses as training targets to fully exploit the spatiotemporal information in multichannel speech data. Second, based on contrastive learning, we use additional single-channel audio data, which is trained jointly to improve the performance of speech representation. Finally, we use a Chinese multichannel multi-modal dataset in real scenarios to validate the effectiveness of the proposed method on audio-visual speech recognition (AVSR), automatic speech recognition (ASR), visual speech recognition (VSR) and audio-visual speaker diarization (AVSD) tasks.
In the realm of automatic speech recognition (ASR), the quest for models that not only perform with high accuracy but also offer transparency in their decision-making processes is crucial. The potential of quality estimation (QE) metrics is introduced and evaluated as a novel tool to enhance explainable artificial intelligence (XAI) in ASR systems. Through experiments and analyses, the capabilities of the NoRefER (No Reference Error Rate) metric are explored in identifying word-level errors to aid post-editors in refining ASR hypotheses. The investigation also extends to the utility of NoRefER in the corpus-building process, demonstrating its effectiveness in augmenting datasets with insightful annotations. The diagnostic aspects of NoRefER are examined, revealing its ability to provide valuable insights into model behaviors and decision patterns. This has proven beneficial for prioritizing hypotheses in post-editing workflows and fine-tuning ASR models. The findings suggest that NoRefER is not merely a tool for error detection but also a comprehensive framework for enhancing ASR systems' transparency, efficiency, and effectiveness. To ensure the reproducibility of the results, all source codes of this study are made publicly available.
Research on speech recognition has attracted considerable interest due to the difficult task of segmenting uninterrupted speech. Among various languages, Bengali features distinct rhythmic patterns and tones, making it particularly difficult to recognize and lacking an efficient commercial recognition method. In order to improve the automatic speech recognition model for Bengali, our team has chosen to utilize the wave2vec 2.0 pre-trained model, which has undergone convergence for fine-tuning. Regarding Word Error Rate (WER), the learning rate and dropout parameters were fine-tuned, and after the model training was stable, attempts were made to enlarge the training set ratio, which improved the model's performance. Consequently, there was a notable enhancement in the WER from 0.508 to 0.437 on the test set of the publicly listed official dataset. Afterwards, the training and validation sets were merged, creating a comprehensive dataset that was used as the training set, achieving a remarkable WER of 0.436.