Serialized Output Training by Learned Dominance

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods have relied on either the Permutation Invariant Training (PIT) or the time-based First-In-First-Out (FIFO) rule. This study presents a model-based serialization strategy that incorporates an auxiliary module into the Attention Encoder-Decoder architecture, autonomously identifying the crucial factors to order the output sequence of the speech components in multi-talker speech. Experiments conducted on the LibriSpeech and LibriMix databases reveal that our approach significantly outperforms the PIT and FIFO baselines in both 2-mix and 3-mix scenarios. Further analysis shows that the serialization module identifies dominant speech components in a mixture by factors including loudness and gender, and orders speech components based on the dominance score.

CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge

The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.

SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition

Deploying a well-optimized pre-trained speaker recognition model in a new domain often leads to a significant decline in performance. While fine-tuning is a commonly employed solution, it demands ample adaptation data and suffers from parameter inefficiency, rendering it impractical for real-world applications with limited data available for model adaptation. Drawing inspiration from the success of adapters in self-supervised pre-trained models, this paper introduces a SE/BN adapter to address this challenge. By freezing the core speaker encoder and adjusting the feature maps' weights and activation distributions, we introduce a novel adapter utilizing trainable squeeze-and-excitation (SE) blocks and batch normalization (BN) layers, termed SE/BN adapter. Our experiments, conducted using VoxCeleb for pre-training and 4 genres from CN-Celeb for adaptation, demonstrate that the SE/BN adapter offers significant performance improvement over the baseline and competes with the vanilla fine-tuning approach by tuning just 1% of the parameters.

Zero-Shot Fake Video Detection by Audio-Visual Consistency

Recent studies have advocated the detection of fake videos as a one-class detection task, predicated on the hypothesis that the consistency between audio and visual modalities of genuine data is more significant than that of fake data. This methodology, which solely relies on genuine audio-visual data while negating the need for forged counterparts, is thus delineated as a `zero-shot' detection paradigm. This paper introduces a novel zero-shot detection approach anchored in content consistency across audio and video. By employing pre-trained ASR and VSR models, we recognize the audio and video content sequences, respectively. Then, the edit distance between the two sequences is computed to assess whether the claimed video is genuine. Experimental results indicate that, compared to two mainstream approaches based on semantic consistency and temporal consistency, our approach achieves superior generalizability across various deepfake techniques and demonstrates strong robustness against audio-visual perturbations. Finally, state-of-the-art performance gains can be achieved by simply integrating the decision scores of these three systems.

A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition

Data augmentation (DA) has played a pivotal role in the success of deep speaker recognition. Current DA techniques primarily focus on speaker-preserving augmentation, which does not change the speaker trait of the speech and does not create new speakers. Recent research has shed light on the potential of speaker augmentation, which generates new speakers to enrich the training dataset. In this study, we delve into two speaker augmentation approaches: speed perturbation (SP) and vocal tract length perturbation (VTLP). Despite the empirical utilization of both methods, a comprehensive investigation into their efficacy is lacking. Our study, conducted using two public datasets, VoxCeleb and CN-Celeb, revealed that both SP and VTLP are proficient at generating new speakers, leading to significant performance improvements in speaker recognition. Furthermore, they exhibit distinct properties in sensitivity to perturbation factors and data complexity, hinting at the potential benefits of their fusion. Our research underscores the substantial potential of speaker augmentation, highlighting the importance of in-depth exploration and analysis.

How phonemes contribute to deep speaker models?

Which phonemes convey more speaker traits is a long-standing question, and various perception experiments were conducted with human subjects. For speaker recognition, studies were conducted with the conventional statistical models and the drawn conclusions are more or less consistent with the perception results. However, which phonemes are more important with modern deep neural models is still unexplored, due to the opaqueness of the decision process. This paper conducts a novel study for the attribution of phonemes with two types of deep speaker models that are based on TDNN and CNN respectively, from the perspective of model explanation. Specifically, we conducted the study by two post-explanation methods: LayerCAM and Time Align Occlusion (TAO). Experimental results showed that: (1) At the population level, vowels are more important than consonants, confirming the human perception studies. However, fricatives are among the most unimportant phonemes, which contrasts with previous studies. (2) At the speaker level, a large between-speaker variation is observed regarding phoneme importance, indicating that whether a phoneme is important or not is largely speaker-dependent.

Adversarial Data Augmentation for Robust Speaker Verification

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural networks to learn speaker-related representations while disregarding irrelevant acoustic variations, thereby improving robustness and generalization. However, a potential issue with the vanilla DA is augmentation residual, i.e., unwanted distortion caused by different types of augmentation. To address this problem, this paper proposes a novel approach called adversarial data augmentation (A-DA) which combines DA with adversarial learning. Specifically, it involves an additional augmentation classifier to categorize various augmentation types used in data augmentation. This adversarial learning empowers the network to generate speaker embeddings that can deceive the augmentation classifier, making the learned speaker embeddings more robust in the face of augmentation variations. Experiments conducted on VoxCeleb and CN-Celeb datasets demonstrate that our proposed A-DA outperforms standard DA in both augmentation matched and mismatched test conditions, showcasing its superior robustness and generalization against acoustic variations.

A Glance is Enough: Extract Target Sentence By Looking at A keyword

This paper investigates the possibility of extracting a target sentence from multi-talker speech using only a keyword as input. For example, in social security applications, the keyword might be "help", and the goal is to identify what the person who called for help is articulating while ignoring other speakers. To address this problem, we propose using the Transformer architecture to embed both the keyword and the speech utterance and then rely on the cross-attention mechanism to select the correct content from the concatenated or overlapping speech. Experimental results on Librispeech demonstrate that our proposed method can effectively extract target sentences from very noisy and mixed speech (SNR=-3dB), achieving a phone error rate (PER) of 26\%, compared to the baseline system's PER of 96%.

An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition

Multi-genre speaker recognition is becoming increasingly popular due to its ability to better represent the complexities of real-world applications. However, a major challenge is the significant shift in the distribution of speaker vectors across different genres. While distribution alignment is a common approach to address this challenge, previous studies have mainly focused on aligning a source domain with a target domain, and the performance of multi-genre data is unknown. This paper presents a comprehensive study of mainstream distribution alignment methods on multi-genre data, where multiple distributions need to be aligned. We analyze various methods both qualitatively and quantitatively. Our experiments on the CN-Celeb dataset show that within-between distribution alignment (WBDA) performs relatively better. However, we also found that none of the investigated methods consistently improved performance in all test cases. This suggests that solely aligning the distributions of speaker vectors may not fully address the challenges posed by multi-genre speaker recognition. Further investigation is necessary to develop a more comprehensive solution.

Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue, almost all present methods focus on a simple configuration where the model is trained in one domain and deployed in another. However, real-world environments are often complex and may contain multiple domains, making the methods designed for one-to-one adaptation suboptimal. In our paper, we propose a self-supervised learning method to tackle this multi-domain adaptation problem. Building upon the basic self-supervised adaptation algorithm, we designed three strategies to make it suitable for multi-domain adaptation: an in-domain negative sampling strategy, a MoCo-like memory bank scheme, and a CORAL-like distribution alignment. We conducted experiments using VoxCeleb2 as the source domain dataset and CN-Celeb1 as the target multi-domain dataset. Our results demonstrate that our method clearly outperforms the basic self-supervised adaptation method, which simply treats the data of CN-Celeb1 as a single domain. Importantly, the improvement is consistent in nearly all in-domain tests and cross-domain tests, demonstrating the effectiveness of our proposed method.