Speech emotion recognition (SER) is a crucial research topic in human-computer interactions. Existing works are mainly based on manually designed models. Despite their great success, these methods heavily rely on historical experience, which are time-consuming but cannot exhaust all possible structures. To address this problem, we propose a neural architecture search (NAS) based framework for SER, called "EmotionNAS". We take spectrogram and wav2vec features as the inputs, followed with NAS to optimize the network structure for these features separately. We further incorporate complementary information in these features through decision-level fusion. Experimental results on IEMOCAP demonstrate that our method succeeds over existing state-of-the-art strategies on SER.
The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while the neural vocoders have the advantage of high synthesis quality. To combine the advantages of two vocoders, inspired by the traditional deterministic plus stochastic model, this paper proposes a novel neural vocoder named NeuralDPS which can retain high speech quality and acquire high synthesis efficiency and noise controllability. Firstly, this framework contains four modules: a deterministic source module, a stochastic source module, a neural V/UV decision module and a neural filter module. The input required by the vocoder is just the spectral parameter, which avoids the error caused by estimating additional parameters, such as F0. Secondly, to solve the problem that different frequency bands may have different proportions of deterministic components and stochastic components, a multiband excitation strategy is used to generate a more accurate excitation signal and reduce the neural filter's burden. Thirdly, a method to control noise components of speech is proposed. In this way, the signal-to-noise ratio (SNR) of speech can be adjusted easily. Objective and subjective experimental results show that our proposed NeuralDPS vocoder can obtain similar performance with the WaveNet and it generates waveforms at least 280 times faster than the WaveNet vocoder. It is also 28% faster than WaveGAN's synthesis efficiency on a single CPU core. We have also verified through experiments that this method can effectively control the noise components in the predicted speech and adjust the SNR of speech. Examples of generated speech can be found at https://hairuo55.github.io/NeuralDPS.
Conversations have become a critical data format on social media platforms. Understanding conversation from emotion, content, and other aspects also attracts increasing attention from researchers due to its widespread application in human-computer interaction. In real-world environments, we often encounter the problem of incomplete modalities, which has become a core issue of conversation understanding. To address this problem, researchers propose various methods. However, existing approaches are mainly designed for individual utterances or medical images rather than conversational data, which cannot exploit temporal and speaker information in conversations. To this end, we propose a novel framework for incomplete multimodal learning in conversations, called "Graph Complete Network (GCNet)", filling the gap of existing works. Our GCNet contains two well-designed graph neural network-based modules, "Speaker GNN" and "Temporal GNN", to capture temporal and speaker information in conversations. To make full use of complete and incomplete data in feature learning, we jointly optimize classification and reconstruction in an end-to-end manner. To verify the effectiveness of our method, we conduct experiments on three benchmark conversational datasets. Experimental results demonstrate that our GCNet is superior to existing state-of-the-art approaches in incomplete multimodal learning.
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.
The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural due to cut-copy-paste operation. In addition, it is not obvious how to synthesize records according to a new word not appearing in the transcript. This paper proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet). The model can simulate the text-based speech editing process by randomly masking part of speech and then predicting the masked region by sensing the speech context. It can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript. Secondly, for the possible operation of text-based speech editing, we design three text-based operations based on CampNet: deletion, insertion, and replacement. These operations can cover various situations of speech editing. Thirdly, to synthesize the speech corresponding to long text in insertion and replacement operations, a word-level autoregressive generation method is proposed. Fourthly, we propose a speaker adaptation method using only one sentence for CampNet and explore the ability of few-shot learning based on CampNet, which provides a new idea for speech forgery tasks. The subjective and objective experiments on VCTK and LibriTTS datasets show that the speech editing results based on CampNet are better than TTS technology, manual editing, and VoCo method. We also conduct detailed ablation experiments to explore the effect of the CampNet structure on its performance. Finally, the experiment shows that speaker adaptation with only one sentence can further improve the naturalness of speech. Examples of generated speech can be found at https://hairuo55.github.io/CampNet.
Knowledge graph embedding~(KGE) aims to represent entities and relations into low-dimensional vectors for many real-world applications. The representations of entities and relations are learned via contrasting the positive and negative triplets. Thus, high-quality negative samples are extremely important in KGE. However, the present KGE models either rely on simple negative sampling methods, which makes it difficult to obtain informative negative triplets; or employ complex adversarial methods, which requires more training data and strategies. In addition, these methods can only construct negative triplets using the existing entities, which limits the potential to explore harder negative triplets. To address these issues, we adopt mixing operation in generating harder negative samples for knowledge graphs and introduce an inexpensive but effective method called MixKG. Technically, MixKG first proposes two kinds of criteria to filter hard negative triplets among the sampled negatives: based on scoring function and based on correct entity similarity. Then, MixKG synthesizes harder negative samples via the convex combinations of the paired selected hard negatives. Experiments on two public datasets and four classical KGE methods show MixKG is superior to previous negative sampling algorithms.
End-to-end singing voice synthesis (SVS) is attractive due to the avoidance of pre-aligned data. However, the auto learned alignment of singing voice with lyrics is difficult to match the duration information in musical score, which will lead to the model instability or even failure to synthesize voice. To learn accurate alignment information automatically, this paper proposes an end-to-end SVS framework, named Singing-Tacotron. The main difference between the proposed framework and Tacotron is that the speech can be controlled significantly by the musical score's duration information. Firstly, we propose a global duration control attention mechanism for the SVS model. The attention mechanism can control each phoneme's duration. Secondly, a duration encoder is proposed to learn a set of global transition tokens from the musical score. These transition tokens can help the attention mechanism decide whether moving to the next phoneme or staying at each decoding step. Thirdly, to further improve the model's stability, a dynamic filter is designed to help the model overcome noise interference and pay more attention to local context information. Subjective and objective evaluation verify the effectiveness of the method. Furthermore, the role of global transition tokens and the effect of duration control are explored. Examples of experiments can be found at https://hairuo55.github.io/SingingTacotron.
Code-switching is about dealing with alternative languages in the communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is known to be a challenging problem because of the lack of data compounded by the increased language context confusion due to the presence of more than one language. In this paper, we propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint Theory (EC). The linguistic theory requires that any monolingual fragment that occurs in the code-switching sentence must occur in one of the monolingual sentences. It establishes a bridge between monolingual data and code-switching data. By calculating the respective attention of multiple languages, our method can efficiently transfer language knowledge from rich monolingual data. We evaluate our method on ASRU 2019 Mandarin-English code-switching challenge dataset. Compared with the baseline model, the proposed method achieves 11.37% relative mix error rate reduction.
Knowledge Graphs (KGs) have shown great success in recommendation. This is attributed to the rich attribute information contained in KG to improve item and user representations as side information. However, existing knowledge-aware methods leverage attribute information at a coarse-grained level both in item and user side. In this paper, we proposed a novel attentive knowledge graph attribute network(AKGAN) to learn item attributes and user interests via attribute information in KG. Technically, AKGAN adopts a heterogeneous graph neural network framework, which has a different design between the first layer and the latter layer. With one attribute placed in the corresponding range of element-wise positions, AKGAN employs a novel interest-aware attention network, which releases the limitation that the sum of attention weight is 1, to model the complexity and personality of user interests towards attributes. Experimental results on three benchmark datasets show the effectiveness and explainability of AKGAN.