In Spoken language understanding (SLU), a natural solution is concatenating pre-trained speech models (e.g. HuBERT) and pretrained language models (PLM, e.g. T5). Most previous works use pretrained language models with subword-based tokenization. However, the granularity of input units affects the alignment of speech model outputs and language model inputs, and PLM with character-based tokenization is underexplored. In this work, we conduct extensive studies on how PLMs with different tokenization strategies affect spoken language understanding task including spoken question answering (SQA) and speech translation (ST). We further extend the idea to create T5lephone(pronounced as telephone), a variant of T5 that is pretrained using phonemicized text. We initialize T5lephone with existing PLMs to pretrain it using relatively lightweight computational resources. We reached state-of-the-art on NMSQA, and the T5lephone model exceeds T5 with other types of units on end-to-end SQA and ST.
Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. However, it requires high computing resources, making it impractical for real-world applications. This paper proposed an MTDVocaLiST model, which is trained by our proposed multimodal Transformer distillation (MTD) loss. MTD loss enables MTDVocaLiST model to deeply mimic the cross-attention distribution and value-relation in the Transformer of VocaLiST. Our proposed method is effective in two aspects: From the distillation method perspective, MTD loss outperforms other strong distillation baselines. From the distilled model's performance perspective: 1) MTDVocaLiST outperforms similar-size SOTA models, SyncNet, and PM models by 15.69% and 3.39%; 2) MTDVocaLiST reduces the model size of VocaLiST by 83.52%, yet still maintaining similar performance.
Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar performance as original SSL models, distilled counterparts suffer from performance degradation even more than their original versions in distorted environments. This paper proposes to apply Cross-Distortion Mapping and Domain Adversarial Training to SSL models during knowledge distillation to alleviate the performance gap caused by the domain mismatch problem. Results show consistent performance improvements under both in- and out-of-domain distorted setups for different downstream tasks while keeping efficient model size.
We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and implements metrics to measure the computation requirements of self-supervised learning (SSL) representation and to evaluate its generalizability and performance across the diverse SUPERB tasks. The SUPERB benchmark provides comprehensive coverage of popular speech processing tasks, from speech and speaker recognition to audio generation and semantic understanding. As SSL has gained interest in the speech community and showed promising outcomes, we envision the challenge to uplevel the impact of SSL techniques by motivating more practical designs of techniques beyond task performance. We summarize the results of 14 submitted models in this paper. We also discuss the main findings from those submissions and the future directions of SSL research.
Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in reducing the computational cost. In this work, we study fixed-length and variable-length subsampling along the time axis in self-supervised learning. We explore how individual downstream tasks are sensitive to input frame rates. Subsampling while training self-supervised models not only improves the overall performance on downstream tasks under certain frame rates, but also brings significant speed-up in inference. Variable-length subsampling performs particularly well under low frame rates. In addition, if we have access to phonetic boundaries, we find no degradation in performance for an average frame rate as low as 10 Hz.
Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects of information latently present in speech signals. However, relatively little is known about the suitability of such models for prosody-related tasks or the extent to which they encode prosodic information. We present a new evaluation framework, SUPERB-prosody, consisting of three prosody-related downstream tasks and two pseudo tasks. We find that 13 of the 15 SSL models outperformed the baseline on all the prosody-related tasks. We also show good performance on two pseudo tasks: prosody reconstruction and future prosody prediction. We further analyze the layerwise contributions of the SSL models. Overall we conclude that SSL speech models are highly effective for prosody-related tasks.
In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. However, fine-tuning pre-trained models for each downstream task is parameter-inefficient since SSL models are notoriously large with millions of parameters. Adapters are lightweight modules commonly used in NLP to solve this problem. In downstream tasks, the parameters of SSL models are frozen, and only the adapters are trained. Given the lack of studies generally exploring the effectiveness of adapters for self-supervised speech tasks, we intend to fill this gap by adding various adapter modules in pre-trained speech SSL models. We show that the performance parity can be achieved with over 90% parameter reduction, and discussed the pros and cons of efficient tuning techniques. This is the first comprehensive investigation of various adapter types across speech tasks.
In this paper, we explore the following question: how far are we from real synonym substitution attacks (SSAs). We approach this question by examining how SSAs replace words in the original sentence and show that there are still unresolved obstacles that make current SSAs generate invalid adversarial samples. We reveal that four widely used word substitution methods generate a large fraction of invalid substitution words that are ungrammatical or do not preserve the original sentence's semantics. Next, we show that the semantic and grammatical constraints used in SSAs for detecting invalid word replacements are highly insufficient in detecting invalid adversarial samples. Our work is an important stepping stone to constructing better SSAs in the future.
Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, not to mention the effective defense against such attacks. In this paper, we are the first to reveal the vulnerability of AVASD models under audio-only, visual-only, and audio-visual adversarial attacks through extensive experiments. What's more, we also propose a novel audio-visual interaction loss (AVIL) for making attackers difficult to find feasible adversarial examples under an allocated attack budget. The loss aims at pushing the inter-class embeddings to be dispersed, namely non-speech and speech clusters, sufficiently disentangled, and pulling the intra-class embeddings as close as possible to keep them compact. Experimental results show the AVIL outperforms the adversarial training by 33.14 mAP (%) under multi-modal attacks.
Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover, SpeechCLIP can directly retrieve semantically related keywords from speech.