Speaker Normalization for Self-supervised Speech Emotion Recognition
Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obtain new state-of-the-art results on the challenging IEMOCAP dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Emotion RecognitionSpeech Emotion RecognitionSimilar Papers 제목 키워드 기반
Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
In expressive speech synthesis, there are high requirements for emotion interpretation. However, it is time-consuming to acquire emotional audio corpus for arbitrary speakers due to their deduction ability. In response t…
Emotion InterpretationExpressive Speech SynthesisSpeech Synthesistext-to-speech+1DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
Cross-speaker emotion transfer in speech synthesis relies on extracting speaker-independent emotion embeddings for accurate emotion modeling without retaining speaker traits. However, existing timbre compression methods …
AttributeEmotional Speech SynthesisSpeech Synthesistext-to-speech+1In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesis
Speech emotion conversion aims to convert the expressed emotion of a spoken utterance to a target emotion while preserving the lexical information and the speaker's identity. In this work, we specifically focus on in-the…
ResynthesisConverting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Model
Expressive voice conversion (VC) conducts speaker identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Emotional style modeling for arbitrary speakers in expressive VC ha…
DenoisingEmotion RecognitionSpeaker VerificationSpeech Emotion Recognition+1Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations
Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these speech representations across time is typ…
DescriptiveSelf-Supervised Learning