A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation

By Guoning Hu, Deliang Wang. IEEE Transactions on Audio, Speech, and Language Processing, 2010

307 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/862cf47cf5737cd8777ce90b2db079a16fc4e184

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Deliang Wang
2. Yuxuan Wang
3. Zhuo Chen
4. Yuzhou Liu
5. Yi Luo
6. Nima Mesgarani
7. Kun Han
8. Kazuhito Koishida

In Signal Processing

1. Nima Mesgarani
2. Deliang Wang
3. Xu Tan
4. Yi Luo
5. Zhuo Chen
6. Tao Qin
7. Tie-Yan Liu
8. Yi Ren

Citations in the corpus

• Exploring Monaural Features for Classification-Based Speech Segregation (2013, methodology): “In our experiments, we use a set of pitch-based features originally proposed in [12], and its effectiveness has been confirmed in both anechoic and reverberant environments with additive noise [14, 17].”
• Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation (2019, methodology): “example, a tandem algorithm [14] utilizes pitch for simultaneous”
• MMTM: Multimodal Transfer Module for CNN Fusion (2019, methodology): “In addition, CHiME-1/3 [65, 66], NonStationaryNoise [67], ESC50 [68], HuCorpus [69], and private datasets are used for additive noise.”
• SpeechNet: A Universal Modularized Model for Speech Processing Tasks (2021, methodology): “For SE, Nonspeech (Hu and Wang, 2010) is a widely used noise dataset containing 100 types of noises.”
• Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling (2020, methodology): “For artificial noisy dataset, we use the VCTK corpus [11] as the clean speech and the Nonspeech100 [12] for background noise.”
• A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models (2011, background): “Methods for multipitch tracking o f speech include [1], [15], [16], [17] and recently [18].”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “For 128 example, the tandem algorithm separates voiced speech by 129 alternating pitch estimation and pitch-based grouping [78].”
• Towards Scaling Up Classification-Based Speech Separation (2013, methodology): “The IBM-modulated SNR is considered a more appropriate measure [24], as the IBM represents the ground truth of classification.”
• Speaker-Independent Speech Separation With Deep Attractor Network (2017, methodology): “s pitch and signal continuity are estimated from the observation and used to separate the target signal from other sources in the mixture. Methods such as computational auditory scene analysis (CASA) [11], [12] and spectral clustering [13] fall into this category [14]. Factorization models, such as ”