Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against different acoustic distortions. Recently, personalization of ASR models on mobile devices has been shown to improve Word Error Rate (WER). This paper evaluates data augmentation in this context and proposes persoDA; a DA method driven by user’s data utilized to personalize ASR [1] –[3]. persoDA aims to augment training with data specifically tuned towards acoustic characteristics of the end-user, as opposed to standard augmentation based on Multi-Condition Training (MCT) that applies random reverberation and noises. Our evaluation with an ASR conformer-based baseline trained on Librispeech and per-sonalized for VOICES [4] shows that persoDA achieves a 13.9% relative WER reduction over using standard data augmentation (using random noise & reverberation). Furthermore, persoDA shows 16% to 20% faster convergence over MCT.

Diffusion based Text-To-Music (TTM) models generate music corresponding to text descriptions. Typically UNet based diffusion models condition on text embeddings generated from a pre-trained large language model or from a cross-modality audio-language representation model. This work proposes a diffusion based TTM, in which the UNet is conditioned on both (i) a uni-modal language model (e.g., T5) via cross-attention and (ii) a cross-modal audio-language representation model (e.g., CLAP) via Feature-wise Linear Modulation (FiLM). The diffusion model is trained to exploit both a local text representation from the T5 and a global representation from the CLAP. Furthermore, we propose modifications that extract both global and local representations from the T5 through pooling mechanisms that we call mean pooling and self-attention pooling. This approach mitigates the need for an additional encoder (e.g., CLAP) to extract a global representation, thereby reducing the number of model parameters. Our results show that incorporating the CLAP global embeddings to the T5 local embeddings enhances text adherence (KL=1.47) compared to a baseline model solely relying on the T5 local embeddings (KL=1.54). Alternatively, extracting global text embeddings directly from the T5 local embeddings through the proposed mean pooling approach yields superior generation quality (FAD=1.89) while exhibiting marginally inferior text adherence (KL=1.51) against the model conditioned on both CLAP and T5 text embeddings (FAD=1.94 and KL=1.47). Our proposed solution is not only efficient but also compact in terms of the number of parameters required.

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are selected from a large pool of phrases following a sampling strategy. In this work we firstly analyse different sampling strategies to provide insights into the training of CB for ASR with correlation plots between the bias embeddings among various training stages. Secondly, we introduce a neighbourhood attention (NA) that localizes self attention (SA) to the nearest neighbouring frames to further refine the CB output. The results show that this proposed approach provides on average a 25.84% relative WER improvement on LibriSpeech sets and rare-word evaluation compared to the baseline.

On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training. This is due to a domain shift between user data and the original training data, differed by user’s speaking characteristics and environmental acoustic conditions. ASR personalisation is a solution that aims to exploit user data to improve model robustness. The majority of ASR personalisation methods assume labelled user data for supervision. Personalisation without any labelled data is challenging due to limited data size and poor quality of recorded audio samples. This work addresses unsupervised personalisation by developing a novel consistency based training method via pseudo-labelling. Our method achieves a relative Word Error Rate Reduction (WERR) of 17.3% on unlabelled training data and 8.1% on held-out data compared to a pre-trained model, and outperforms the current state-of-the art methods.

Knowledge distillation (KD) has widely been used for model compression and domain adaptation for speech applications. In the presence of multiple teachers, knowledge can easily be transferred to the student by averaging the models output. However, previous research shows that the student do not adapt well with such combination. This paper propose to use an elitist sampling strategy at the output of ensemble teacher models to select the best-decoded utterance generated by completely out-of-domain teacher models for generalizing unseen domain. The teacher models are trained on AMI, LibriSpeech and WSJ while the student is adapted for the Switchboard data. The results show that with the selection strategy based on the individual model’s posteriors the student model achieves a better WER compared to all the teachers and baselines with a minimum absolute improvement of about 8.4%. Furthermore, an insights on the model adaptation with out-of-domain data has also been studied via correlation analysis.

The Goodness of Pronunciation (GOP) algorithm is one well-established method of pronunciation assessment dependent on precise phoneme segment boundaries. The alignment process of canonical pronunciations to obtain these boundaries is prone to errors. To overcome this issue, the present paper proposes a combination of Bidirectional Long-Short Memory with saliency region selection with attention weights to provide estimates of mispronunciations without the need of phoneme boundaries. Three output and annotation configurations were used to train the model which was then assessed against a GOP baseline in the task of detecting segments with mispronunciations. The experiments were conducted using data from young Dutch learners of English, annotated by three trained phoneticians. The proposed model outperformed the GOP baseline. It was also found that the attention weights aligned themselves with the phoneme labels, helping detect mispronunciations and allowing further interpretation of the internal representation of the model.

Generative Adversarial Networks (GANs) are machine learning networks based around creating synthetic data. Voice Conversion (VC) is a subset of voice translation that involves translating the paralinguistic features of a source speaker to a target speaker while preserving the linguistic information. The aim of non-parallel conditional GANs for VC is to translate an acoustic speech feature sequence from one domain to another without the use of paired data. In the study reported here, we investigated the interpretability of state-of-the-art implementations of non-parallel GANs in the domain of VC. We show that the learned representations in the repeating layers of a particular GAN architecture remain close to their original random initialised parameters, demonstrating that it is the number of repeating layers that is more responsible for the quality of the output. We also analysed the learned representations of a model trained on one particular dataset when used during transfer learning on another dataset. This showed extremely high levels of similarity across the entire network. Together, these results provide new insight into how the learned representations of deep generative networks change during learning and the importance in the number of layers.

End-to-end automatic speech recognition (ASR) models aim to learn a generalised speech representation. However, there are limited tools available to understand the internal functions and the effect of hierarchical dependencies within the model architecture. It is crucial to understand the correlations between the layer-wise representations, to derive insights on the relationship between neural representations and performance. Previous investigations of network similarities using correlation analysis techniques have not been explored for End-to-End ASR models. This paper analyses and explores the internal dynamics between layers during training with CNN, LSTM and Transformer based approaches using Canonical correlation analysis (CCA) and centered kernel alignment (CKA) for the experiments. It was found that neural representations within CNN layers exhibit hierarchical correlation dependencies as layer depth increases but this is mostly limited to cases where neural representation correlates more closely. This behaviour is not observed in LSTM architecture, however there is a bottom-up pattern observed across the training process, while Transformer encoder layers exhibit irregular coefficiency correlation as neural depth increases. Altogether, these results provide new insights into the role that neural architectures have upon speech recognition performance. More specifically, these techniques can be used as indicators to build better performing speech recognition models.

Speech emotion recognition is essential for obtaining emotional intelligence which affects the understanding of context and meaning of speech. Harmonically structured vowel and consonant sounds add indexical and linguistic cues in spoken information. Previous research argued whether vowel sound cues were more important in carrying the emotional context from a psychological and linguistic point of view. Other research also claimed that emotion information could exist in small overlapping acoustic cues. However, these claims are not corroborated in computational speech emotion recognition systems. In this research, a convolution-based model and a long-short-term memory-based model, both using attention, are applied to investigate these theories of speech emotion on computational models. The role of acoustic context and word importance is demonstrated for the task of speech emotion recognition. The IEMOCAP corpus is evaluated by the proposed models, and 80.1% unweighted accuracy is achieved on pure acoustic data which is higher than current state-of-the-art models on this task. The phones and words are mapped to the attention vectors and it is seen that the vowel sounds are more important for defining emotion acoustic cues than the consonants, and the model can assign word importance based on acoustic context.

Speech emotion recognition is essential for obtaining emotional intelligence which affects the understanding of context and meaning of speech. The fundamental challenges of speech emotion recognition from a machine learning standpoint is to extract patterns which carry maximum correlation with the emotion information encoded in this signal, and to be as insensitive as possible to other types of information carried by speech. In this paper, a novel recurrent residual temporal context modelling framework is proposed. The framework includes mixture of multi-view attention smoothing and high dimensional feature projection for context expansion and learning feature representations. The framework is designed to be robust to changes in speaker and other distortions, and it provides state-of-the-art results for speech emotion recognition. Performance of the proposed approach is compared with a wide range of current architectures in a standard 4-class classification task on the widely used IEMOCAP corpus. A significant improvement of 4% unweighted accuracy over state-of-the-art systems is observed. Additionally, the attention vectors have been aligned with the input segments and plotted at two different attention levels to demonstrate the effectiveness.

Speech emotion recognition (SER) is a requisite for emotional intelligence that affects the understanding of speech. One of the most crucial tasks is to obtain patterns having a maximum correlation for the emotion classification task from the speech signal while being invariant to the changes in frequency, time and other external distortions. Therefore, learning emotional contextual feature representation independent of speaker and environment is essential. In this paper, a novel spatiotemporal context modelling framework for robust SER is proposed to learn feature representation by using acoustic context expansion with high dimensional feature projection. The framework uses a deep convolutional neural network (CNN) and self-attention network. The CNNs combine spatiotemporal features. The attention network produces high dimensional task-specific features and combines these features for context modelling, which altogether provides a state-of-the-art technique for classifying the extracted patterns for speech emotion. Speech emotion is a categorical perception representing discrete sensory events. The proposed approach is compared with a wide range of architectures on the RAVDESS and IEMOCAP corpora for 8-class and 4-class emotion classification tasks and remarkable gain over state-of-the-art systems are obtained, absolutely 15%, 10% respectively.

For speech emotion datasets, it has been difficult to acquire large quantities of reliable data and acted emotions may be over the top compared to less expressive emotions displayed in everyday life. Lately, larger datasets with natural emotions have been created. Instead of ignoring smaller, acted datasets, this study investigates whether information learnt from acted emotions is useful for detecting natural emotions. Cross-corpus research has mostly considered cross-lingual and even cross-age datasets, and difficulties arise from different methods of annotating emotions causing a drop in performance. To be consistent, four adult English datasets covering acted, elicited and natural emotions are considered. A state-of-the-art model is proposed to accurately investigate the degradation of performance. The system involves a bi-directional LSTM with an attention mechanism to classify emotions across datasets. Experiments study the effects of training models in a cross-corpus and multi-domain fashion and results show the transfer of information is not successful. Out-of-domain models, followed by adapting to the missing dataset, and domain adversarial training (DAT) are shown to be more suitable to generalising to emotions across datasets. This shows positive information transfer from acted datasets to those with more natural emotions and the benefits from training on different corpora.

This paper proposes the adaptation of neural network-based acoustic models using a Squeeze-and-Excitation (SE) network for automatic speech recognition (ASR). In particular, this work explores to use the SE network to learn utterance-level embeddings. The acoustic modelling is performed using Light Gated Recurrent Units (LiGRU). The utterance embed-dings are learned from hidden unit activations jointly with LiGRU and used to scale respective activations of hidden layers in the LiGRU network. The advantage of such approach is that it does not require domain labels, such as speakers and noise to be known in order to perform the adaptation, thereby providing unsupervised adaptation. The global average and attentive pooling are applied on hidden units to extract utterance-level information that represents the speakers and acoustic conditions. ASR experiments were carried out on the TIMIT and Aurora 4 corpora. The proposed model achieves better performance on both the datasets compared to their respective baselines with relative improvements of 5.59% and 5.54% for TIMIT and Aurora 4 database, respectively. These experiments show the potential of using the conditioning information learned via utterance embeddings in the SE network to adapt acoustic models for speakers, noise, and other acoustic conditions.

Emotion recognition from speech plays a significant role in adding emotional intelligence to machines and making human-machine interaction more natural. One of the key challenges from machine learning standpoint is to extract patterns which bear maximum correlation with the emotion information encoded in this signal while being as insensitive as possible to other types of information carried by speech. In this paper, we propose a novel temporal modelling framework for robust emotion classification using bidirectional long short-term memory network (BLSTM), CNN and Capsule networks. The BLSTM deals with the temporal dynamics of the speech signal by effectively representing forward/backward contextual information while the CNN along with the dynamic routing of the Capsule net learn temporal clusters which altogether provide a state-of-the-art technique for classifying the extracted patterns. The proposed approach was compared with a wide range of architectures on the FAU-Aibo and RAVDESS corpora and remarkable gain over state-of-the-art systems were obtained. For FAO-Aibo and RAVDESS 77.6% and 56.2% accuracy was achieved, respectively, which is 3% and 14% (absolute) higher than the best-reported result for the respective tasks.

Vehicle logo recognition is an important part of vehicle identification in intelligent transportation systems. State-of-the-art vehicle logo recognition approaches use automatically learned features from Convolutional Neural Networks (CNNs). However, CNNs do not perform well when images are rotated and very noisy. This paper proposes an image recognition framework with a capsule network. A capsule is a group of neurons, whose length can represent the existence probability of an entity or part of an entity. The orientation of a capsule contains information about the instantiation parameters such as positions and orientations. Capsules are learned by a routing process, which is more effective than the pooling process in CNNs. This paper, for the first time, develops a capsule learning framework in the field of intelligent transportation systems. By testing with the largest publicly available vehicle logo dataset, the proposed framework gives a quick solution and achieves the highest accuracy (100%) on this dataset. The learning capsules have been tested with different image changes such as rotation and occlusion. Image degradations including blurring and noise effects are also considered, and the proposed framework has proven to be superior to CNNs.

Sign language is a visually oriented, natural, nonverbal communication medium. Having shared similar linguistic properties with its respective spoken language, it consists of a set of gestures, postures and facial expressions. Though, sign language is a mode of communication between deaf people, most other people do not know sign language interpretations. Therefore, it would be constructive if we can translate the sign postures artificially. In this paper, a capsule-based deep neural network sign posture translator for an American Sign Language (ASL) fingerspelling (posture), has been presented. The performance validation shows that the approach can successfully identify sign language, with accuracy like 99%. Unlike previous neural network approaches, which mainly used fine-tuning and transfer learning from pre-trained models, the developed capsule network architecture does not require a pre-trained model. The framework uses a capsule network with adaptive pooling which is the key to its high accuracy. The framework is not limited to sign language understanding, but it has scope for non-verbal communication in Human-Robot Interaction (HRI) also.