Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world applications. Previous works usually studied specific solutions for each scenario from the algorithm perspective. However, the root cause of these problems lies in dataset imperfections. To address these challenges with a unified solution, we propose the Voice Conversion Augmentation (VCA) strategy to obtain pseudo speech from the training set. Furthermore, to guarantee generation quality, we designed the VCA-NN~(nearest neighbours) strategy to select source speech from utterances that are close to the target speech in the representation space. Our experimental results on three created datasets demonstrated that VCA-NN effectively mitigates these dataset problems, which provides a new direction for handling the speaker recognition problems from the data aspect.
This paper summarizes our team's efforts in both tracks of the ICMC-ASR Challenge for in-car multi-channel automatic speech recognition. Our submitted systems for ICMC-ASR Challenge include the multi-channel front-end enhancement and diarization, training data augmentation, speech recognition modeling with multi-channel branches. Tested on the offical Eval1 and Eval2 set, our best system achieves a relative 34.3% improvement in CER and 56.5% improvement in cpCER, compared to the offical baseline system.
We introduce a novel task named `target speech diarization', which seeks to determine `when target event occurred' within an audio signal. We devise a neural architecture called Prompt-driven Target Speech Diarization (PTSD), that works with diverse prompts that specify the target speech events of interest. We train and evaluate PTSD using sim2spk, sim3spk and sim4spk datasets, which are derived from the Librispeech. We show that the proposed framework accurately localizes target speech events. Furthermore, our framework exhibits versatility through its impressive performance in three diarization-related tasks: target speaker voice activity detection, overlapped speech detection and gender diarization. In particular, PTSD achieves comparable performance to specialized models across these tasks on both real and simulated data. This work serves as a reference benchmark and provides valuable insights into prompt-driven target speech processing.
\textit{Objective:} Conventional EEG-based auditory attention detection (AAD) is achieved by comparing the time-varying speech stimuli and the elicited EEG signals. However, in order to obtain reliable correlation values, these methods necessitate a long decision window, resulting in a long detection latency. Humans have a remarkable ability to recognize and follow a known speaker, regardless of the spoken content. In this paper, we seek to detect the attended speaker among the pre-enrolled speakers from the elicited EEG signals. In this manner, we avoid relying on the speech stimuli for AAD at run-time. In doing so, we propose a novel EEG-based attended speaker detection (E-ASD) task. \textit{Methods:} We encode a speaker's voice with a fixed dimensional vector, known as speaker embedding, and project it to an audio-derived voice signature, which characterizes the speaker's unique voice regardless of the spoken content. We hypothesize that such a voice signature also exists in the listener's brain that can be decoded from the elicited EEG signals, referred to as EEG-derived voice signature. By comparing the audio-derived voice signature and the EEG-derived voice signature, we are able to effectively detect the attended speaker in the listening brain. \textit{Results:} Experiments show that E-ASD can effectively detect the attended speaker from the 0.5s EEG decision windows, achieving 99.78\% AAD accuracy, 99.94\% AUC, and 0.27\% EER. \textit{Conclusion:} We conclude that it is possible to derive the attended speaker's voice signature from the EEG signals so as to detect the attended speaker in a listening brain. \textit{Significance:} We present the first proof of concept for detecting the attended speaker from the elicited EEG signals in a cocktail party environment. The successful implementation of E-ASD marks a non-trivial, but crucial step towards smart hearing aids.
In active speaker detection (ASD), we would like to detect whether an on-screen person is speaking based on audio-visual cues. Previous studies have primarily focused on modeling audio-visual synchronization cue, which depends on the video quality of the lip region of a speaker. In real-world applications, it is possible that we can also have the reference speech of the on-screen speaker. To benefit from both facial cue and reference speech, we propose the Target Speaker TalkNet (TS-TalkNet), which leverages a pre-enrolled speaker embedding to complement the audio-visual synchronization cue in detecting whether the target speaker is speaking. Our framework outperforms the popular model, TalkNet on two datasets, achieving absolute improvements of 1.6\% in mAP on the AVA-ActiveSpeaker validation set, and 0.8\%, 0.4\%, and 0.8\% in terms of AP, AUC and EER on the ASW test set, respectively. Code is available at \href{https://github.com/Jiang-Yidi/TS-TalkNet/}{\color{red}{https://github.com/Jiang-Yidi/TS-TalkNet/}}.
Model-based deep learning has achieved astounding successes due in part to the availability of large-scale realworld data. However, processing such massive amounts of data comes at a considerable cost in terms of computations, storage, training and the search for good neural architectures. Dataset distillation has thus recently come to the fore. This paradigm involves distilling information from large real-world datasets into tiny and compact synthetic datasets such that processing the latter yields similar performances as the former. State-of-the-art methods primarily rely on learning the synthetic dataset by matching the gradients obtained during training between the real and synthetic data. However, these gradient-matching methods suffer from the accumulated trajectory error caused by the discrepancy between the distillation and subsequent evaluation. To alleviate the adverse impact of this accumulated trajectory error, we propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7% on a subset of images of the ImageNet dataset with higher resolution images. We also validate the effectiveness and generalizability of our method with datasets of different resolutions and demonstrate its applicability to neural architecture search.
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent from speech without using an intermediate ASR module. However, such end-to-end framework suffers from the unavailability of large speech resources with higher acoustic variation in spoken language understanding. In this work, we exploit the scope of the transformer distillation method that is specifically designed for knowledge distillation from a transformer based language model to a transformer based speech model. In this regard, we leverage the reliable and widely used bidirectional encoder representations from transformers (BERT) model as a language model and transfer the knowledge to build an acoustic model for intent classification using the speech. In particular, a multilevel transformer based teacher-student model is designed, and knowledge distillation is performed across attention and hidden sub-layers of different transformer layers of the student and teacher models. We achieve an intent classification accuracy of 99.10% and 88.79% for Fluent speech corpus and ATIS database, respectively. Further, the proposed method demonstrates better performance and robustness in acoustically degraded condition compared to the baseline method.