Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction. This approach is a paradigm shift from the traditional language model rescoring strategy that can only select one candidate hypothesis as the output transcription. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses and corresponding accurate transcriptions across prevalent speech domains. Given this dataset, we examine three types of error correction techniques based on LLMs with varying amounts of labeled hypotheses-transcription pairs, which gains a significant word error rate (WER) reduction. Experimental evidence demonstrates the proposed technique achieves a breakthrough by surpassing the upper bound of traditional re-ranking based methods. More surprisingly, LLM with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list. We make our results publicly accessible for reproducible pipelines with released pre-trained models, thus providing a new evaluation paradigm for ASR error correction with LLMs.
We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task activation prompting method that combines causal instructions and demonstration to increase its context windows. Next, we show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs, using a pretrained first-pass recognition system and rescoring output on two out-of-domain tasks (ATIS and WSJ). By combining prompting techniques with fine-tuning we achieve error rates below the N-best oracle level, showcasing the generalization power of the LLMs.
We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech transcription contexts. This marks a step towards a fresh paradigm in generative error correction within the realm of n-best hypotheses. Unlike the existing ranking-based rescoring methods, our approach adeptly uses distinct initialization techniques and parameter-efficient algorithms to boost ASR performance derived from pre-trained speech and text models. Through evaluation across diverse ASR datasets, we evaluate the stability and reproducibility of our fusion technique, demonstrating its improved word error rate relative (WERR) performance in comparison to n-best hypotheses by relatively 37.66%. To encourage future research, we have made our code and pre-trained models open source at https://github.com/Srijith-rkr/Whispering-LLaMA.
We explore the ability of large language models (LLMs) to act as ASR post-processors that perform rescoring and error correction. Our focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task-activating prompting (TAP) method that combines instruction and demonstration. Using a pre-trained first-pass system and rescoring output on two out-of-domain tasks (ATIS and WSJ), we show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs. By combining prompting techniques with fine-tuning we achieve error rates below the N-best oracle level, showcasing the generalization power of the LLMs.
We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high computational cost of scaling up the pretraining stage and adapting the pretrained models to specific domains limit their practical use in rescoring. Here we present a method based on low-rank decomposition to train a rescoring BERT model and adapt it to new domains using only a fraction (0.08%) of the pretrained parameters. These inserted matrices are optimized through a discriminative training objective along with a correlation-based regularization loss. The proposed low-rank adaptation Rescore-BERT (LoRB) architecture is evaluated on LibriSpeech and internal datasets with decreased training times by factors between 5.4 and 3.6.
This paper investigates the in-context learning abilities of the Whisper automatic speech recognition (ASR) models released by OpenAI. A novel speech-based in-context learning (SICL) approach is proposed for test-time adaptation, which can reduce the word error rates (WERs) with only a small number of labelled speech samples without gradient descent. Language-level adaptation experiments using Chinese dialects showed that when applying SICL to isolated word ASR, consistent and considerable relative WER reductions can be achieved using Whisper models of any size on two dialects, which is on average 32.3%. A k-nearest-neighbours-based in-context example selection technique can be applied to further improve the efficiency of SICL, which can increase the average relative WER reduction to 36.4%. The findings are verified using speaker adaptation or continuous speech recognition tasks, and both achieved considerable relative WER reductions. Detailed quantitative analyses are also provided to shed light on SICL's adaptability to phonological variances and dialect-specific lexical nuances.
Recently, video summarization has been proposed as a method to help video exploration. However, traditional video summarization models only generate a fixed video summary which is usually independent of user-specific needs and hence limits the effectiveness of video exploration. Multi-modal video summarization is one of the approaches utilized to address this issue. Multi-modal video summarization has a video input and a text-based query input. Hence, effective modeling of the interaction between a video input and text-based query is essential to multi-modal video summarization. In this work, a new causality-based method named Causal Video Summarizer (CVS) is proposed to effectively capture the interactive information between the video and query to tackle the task of multi-modal video summarization. The proposed method consists of a probabilistic encoder and a probabilistic decoder. Based on the evaluation of the existing multi-modal video summarization dataset, experimental results show that the proposed approach is effective with the increase of +5.4% in accuracy and +4.92% increase of F 1- score, compared with the state-of-the-art method.
In this work, we introduce a ``score-based assessment'' framework for estimating the transferability of pre-trained speech models (PSMs) for fine-tuning target tasks. We leverage upon two representation theories, Bayesian likelihood estimation and optimal transport, to generate rank scores for the PSM candidates using the extracted representations. Our framework efficiently computes transferability scores without actual fine-tuning of candidate models or layers by making a temporal independent hypothesis. We evaluate some popular supervised speech models (e.g., Conformer RNN-Transducer) and self-supervised speech models (e.g., HuBERT) in cross-layer and cross-model settings using public data. Experimental results show a high Spearman's rank correlation and low $p$-value between our estimation framework and fine-tuning ground truth. Our proposed transferability framework requires less computational time and resources, making it a resource-saving and time-efficient approach for tuning speech foundation models.
We propose a multi-dimensional structured state space (S4) approach to speech enhancement. To better capture the spectral dependencies across the frequency axis, we focus on modifying the multi-dimensional S4 layer with whitening transformation to build new small-footprint models that also achieve good performance. We explore several S4-based deep architectures in time (T) and time-frequency (TF) domains. The 2-D S4 layer can be considered a particular convolutional layer with an infinite receptive field although it utilizes fewer parameters than a conventional convolutional layer. Evaluated on the VoiceBank-DEMAND data set, when compared with the conventional U-net model based on convolutional layers, the proposed TF-domain S4-based model is 78.6% smaller in size, yet it still achieves competitive results with a PESQ score of 3.15 with data augmentation. By increasing the model size, we can even reach a PESQ score of 3.18.