Phonetic Error Analysis of Raw Waveform Acoustic Models with Parametric and Non-Parametric CNNs

In this paper, we analyse the error patterns of the raw waveform acoustic models in TIMIT's phone recognition task. Our analysis goes beyond the conventional phone error rate (PER) metric. We categorise the phones into three groups: {affricate, diphthong, fricative, nasal, plosive, semi-vowel, vowel, silence}, {consonant, vowel+, silence}, and {voiced, unvoiced, silence} and, compute the PER for each broad phonetic class in each category. We also construct a confusion matrix for each category using the substitution errors and compare the confusion patterns with those of the Filterbank and Wav2vec 2.0 systems. Our raw waveform acoustic models consists of parametric (Sinc2Net) or non-parametric CNNs and Bidirectional LSTMs, achieving down to 13.7%/15.2% PERs on TIMIT Dev/Test sets, outperforming reported PERs for raw waveform models in the literature. We also investigate the impact of transfer learning from WSJ on the phonetic error patterns and confusion matrices. It reduces the PER to 11.8%/13.7% on the Dev/Test sets.

Zero-shot Audio Topic Reranking using Large Language Models

The Multimodal Video Search by Examples (MVSE) project investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content, topic, and emotion. A key element for this process is highly rapid, flexible, search to support large archives, which in MVSE is facilitated by representing video attributes by embeddings. This work aims to mitigate any performance loss from this rapid archive search by examining reranking approaches. In particular, zero-shot reranking methods using large language models are investigated as these are applicable to any video archive audio content. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus. Results demonstrate that reranking can achieve improved retrieval ranking without the need for any task-specific training data.

RCT: Random Consistency Training for Semi-supervised Sound Event Detection

Sound event detection (SED), as a core module of acoustic environmental analysis, suffers from the problem of data deficiency. The integration of semi-supervised learning (SSL) largely mitigates such problem while bringing no extra annotation budget. This paper researches on several core modules of SSL, and introduces a random consistency training (RCT) strategy. First, a self-consistency loss is proposed to fuse with the teacher-student model to stabilize the training. Second, a hard mixup data augmentation is proposed to account for the additive property of sounds. Third, a random augmentation scheme is applied to flexibly combine different types of data augmentations. Experiments show that the proposed strategy outperform other widely-used strategies.

Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers

Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower layers) and retraining the classifier (the upper layers) on the same dataset leads to worse performance. In this paper, for the first time, we show that the frozen classifier is transferable within the same dataset. We develop a novel top-down training method which can be viewed as an algorithm for searching for high-quality classifiers. We tested this method on automatic speech recognition (ASR) tasks and language modelling tasks. The proposed method consistently improves recurrent neural network ASR models on Wall Street Journal, self-attention ASR models on Switchboard, and AWD-LSTM language models on WikiText-2.

On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers

Self-attention models such as Transformers, which can capture temporal relationships without being limited by the distance between events, have given competitive speech recognition results. However, we note the range of the learned context increases from the lower to upper self-attention layers, whilst acoustic events often happen within short time spans in a left-to-right order. This leads to a question: for speech recognition, is a global view of the entire sequence useful for the upper self-attention encoder layers in Transformers? To investigate this, we train models with lower self-attention/upper feed-forward layers encoders on Wall Street Journal and Switchboard. Compared to baseline Transformers, no performance drop but minor gains are observed. We further developed a novel metric of the diagonality of attention matrices and found the learned diagonality indeed increases from the lower to upper encoder self-attention layers. We conclude the global view is unnecessary in training upper encoder layers.

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers

Recently, Transformers have shown competitive automatic speech recognition (ASR) results. One key factor to the success of these models is the multi-head attention mechanism. However, we observed in trained models, the diagonal attention matrices indicating the redundancy of the corresponding attention heads. Furthermore, we found some architectures with reduced numbers of attention heads have better performance. Since the search for the best structure is time prohibitive, we propose to randomly remove attention heads during training and keep all attention heads at test time, thus the final model can be viewed as an average of models with different architectures. This method gives consistent performance gains on the Wall Street Journal, AISHELL, Switchboard and AMI ASR tasks. On the AISHELL dev/test sets, the proposed method achieves state-of-the-art Transformer results with 5.8%/6.3% word error rates.

When Can Self-Attention Be Replaced by Feed Forward Layers?

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability to capture temporal relationships without being limited by the distance between two related events. However, we note that the range of the learned context progressively increases from the lower to upper self-attention layers, whilst acoustic events often happen within short time spans in a left-to-right order. This leads to a question: for speech recognition, is a global view of the entire sequence still important for the upper self-attention layers in the encoder of Transformers? To investigate this, we replace these self-attention layers with feed forward layers. In our speech recognition experiments (Wall Street Journal and Switchboard), we indeed observe an interesting result: replacing the upper self-attention layers in the encoder with feed forward layers leads to no performance drop, and even minor gains. Our experiments offer insights to how self-attention layers process the speech signal, leading to the conclusion that the lower self-attention layers of the encoder encode a sufficiently wide range of inputs, hence learning further contextual information in the upper layers is unnecessary.

Acoustic Model Adaptation from Raw Waveforms with SincNet

Raw waveform acoustic modelling has recently gained interest due to neural networks' ability to learn feature extraction, and the potential for finding better representations for a given scenario than hand-crafted features. SincNet has been proposed to reduce the number of parameters required in raw-waveform modelling, by restricting the filter functions, rather than having to learn every tap of each filter. We study the adaptation of the SincNet filter parameters from adults' to children's speech, and show that the parameterisation of the SincNet layer is well suited for adaptation in practice: we can efficiently adapt with a very small number of parameters, producing error rates comparable to techniques using orders of magnitude more parameters.