Automatic speech emotion recognition has been a research hotspot in the field of human-computer interaction over the past decade. However, due to the lack of research on the inherent temporal relationship of the speech waveform, the current recognition accuracy needs improvement. To make full use of the difference of emotional saturation between time frames, a novel method is proposed for speech recognition using frame-level speech features combined with attention-based long short-term memory (LSTM) recurrent neural networks. Frame-level speech features were extracted from waveform to replace traditional statistical features, which could preserve the timing relations in the original speech through the sequence of frames. To distinguish emotional saturation in different frames, two improvement strategies are proposed for LSTM based on the attention mechanism: first, the algorithm reduces the computational complexity by modifying the forgetting gate of traditional LSTM without sacrificing performance and second, in the final output of the LSTM, an attention mechanism is applied to both the time and the feature dimension to obtain the information related to the task, rather than using the output from the last iteration of the traditional algorithm. Extensive experiments on the CASIA, eNTERFACE, and GEMEP emotion corpora demonstrate that the performance of the proposed approach is able to outperform the state-of-the-art algorithms reported to date.

Because traditional single-channel speech enhancement algorithms are sensitive to the environment and perform poorly, a speech enhancement algorithm based on attention-gated long short-term memory (LSTM) is proposed. To simulate human auditory perceptual characteristics, the algorithm divides the frequency band according to the Bark scale. Based on these bands, bark frequency cepstral coefficients (BFCCs), their derivative features and pitch-based features are extracted. Furthermore, considering that different noises have different influence on the clean speech, the attention mechanism is applied to screen out the information less polluted by noise, which is helpful to reconstruct the clean speech. To adaptively reallocate the power ratio of the speech and noise during the construction of the ratio mask, the ideal ratio mask (IRM) with the inter-channel correlation (ICC) is adopted as the learning target. In addition, to improve the performance of the network, the algorithm introduces a multiobjective learning strategy to jointly optimize the networks by using a voice activity detector (VAD). Subjective and objective experiments show that the proposed algorithm outperforms other baseline algorithms. In real-time experiment, the proposed algorithm maintains high real-time performance and fast convergence speed.

In deep-learning-based speech enhancement (SE) systems, trained models are often used to handle unseen noise types and language environments in real-life scenarios. However, since production environments differ from training conditions, mismatch problems arise that may cause a serious decrease in the performance of an SE system. In this study, a domain adaptive method combining two adaptation strategies is proposed to improve the generalization of unlabeled noisy speech. In the proposed encoder-decoder-based SE framework, a domain discriminator and a domain confusion adaptation layer are introduced to conduct adversarial training. The model has two main innovations. First, the algorithm optimizes adversarial training by introducing a relativistic discriminator that relies on relative values by applying the difference, thus avoiding possible bias and better reflecting domain differences. Second, the multi-kernel maximum mean discrepancy (MK-MMD) between domains is taken as the regularization term of the domain adversarial loss, thereby further decreasing the edge distribution distance between domains. The proposed model improves the adaptability to unseen noises by encouraging the feature encoder to generate domain-invariant features. The model was evaluated using cross-noise and cross-language-and-noise experiments, and the results show that the proposed method provides considerable improvements over the baseline without an adaptation in the perceptual evaluation of speech quality (PESQ), the short time objective intelligibility (STOI) and the frequency-weighted signal-to-noise ratio (FWSNR).

The traditional hearing aid fitting method, which mainly relies on the audiologist, is timeconsuming and messy. To improve this situation, a self-fitting algorithm based on an improved interactive evolutionary computation (IEC) algorithm and expert system, which enables the patients to fit the hearing aid by themselves, is proposed. The algorithm takes the band gain as the fitting target and uses the patient’s subjective evaluation to iteratively update the algorithm parameters based on the improved IEC algorithm. In addition, a real-time updated expert system is constructed to assist in the optimization of the initial and iterative parameters of the fitting based on the patient’s audiogram and personal information. To verify the performance of the algorithm, a self-fitting software for the hearing aid is designed. Through this software, the test signal is generated for the patient to evaluate the audio quality on a five-level scale. Based on the evaluation results, the algorithm iteratively optimizes the algorithm parameters until the patient is satisfied with the generated audio. Compared with the fitting algorithm based on Gaussian processes algorithm or the interactive evolutionary algorithm, the average subjective speech recognition rate of the proposed algorithm increase at least 11%. The average recognition rate for environmental sound is also improved by at least 2.9%. In addition, the fitting time of the proposed algorithm is shortened by at least 10 min compared to others two algorithms.