Recent progresses in deep learning based acoustic models
166 citations recorded by the source corpus.
In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss models such as recurrent neural networks U+0028 RNNs U+0029 and convolutional neural networks U+0028 CNNs U+0029 that can effectively exploit variablelength contextual information, and their various combination with other models. We then describe models that are optimized end-to-end and emphasize on feature representations learned jointly with the rest of the system, the connectionist temporal classification U+0028 CTC U+0029 criterion, and the attention-based sequenceto-sequence translation model. We further illustrate robustness issues in speech recognition systems, and discuss acoustic model adaptation, speech enhancement and separation, and robust training strategies. We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Signal Processing
Citations in the corpus
- Three Approaches for Personalization with Applications to Federated Learning (2020, background): “Personalization of machine learning models has been studied extensively for specific applications such as speech recognition (Yu and Li, 2017).”
- Salvaging Federated Learning by Local Adaptation (2020, methodology): “Prior work on personalization of ML models focused on speaker adaptation of acoustic models (see (Yu & Li, 2017)).”
- An Introductory Review of Deep Learning for Prediction Models With Big Data (2020, background): “…a historic summary with many detailed references in Schmidhuber (2015) and reviews about application domains, e.g., image analysis (Rawat and Wang, 2017; Shen et al., 2017), speech recognition (Yu and Li, 2017), natural language processing (Young et al., 2018), and biomedicine (Cao et al., 2018).”
- Cycle-Consistent Speech Enhancement (2018, background): “We pre-train a clean DNN acoustic model as in Section 3.2 of [31] using 9137 clean training utterances in CHiME-3 to evaluate the ASR word error rate (WER) performance of the test features enhanced by F .”
- Cracking the cocktail party problem by multi-beam deep attractor network (2017, background): “Prior to the deep learning era [4, 5, 6, 7, 8, 9], several attempts were made.”
- SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts (2021, background): “Owing to powerful representation, Deep Neural Networks (DNN) have gained great success in speech recognition [1, 2].”
- Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition (2018, background): “Although the seq2seq models have shown success in speech recognition task, they still suffer from a drawback: slow training speed [13].”
- IoT Wearable Sensor and Deep Learning: An Integrated Approach for Personalized Human Activity Recognition in a Smart Home Environment (2019, background): “The state-of-the-art of deep learning architectures are represented by RNNs and CNNs [37], [38].”
- Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition (2018, unknown): “A wide range of DNN adaptation techniques for robust ASR are described in [4, 5].”
- Unsupervised adaptation with domain separation networks for robust speech recognition (2017, background): “Table 1 shows the WER performance of clean, GRL adapted and DSN adapted DNN acoustic models for ASR.”
- Speaker-Invariant Training Via Adversarial Learning (2018, methodology): “The deep neural network (DNN) based acoustic models have been widely used in automatic speech recognition (ASR) and have achieved extraordinary performance improvement [1, 2].”