A review on speech separation in cocktail party environment: challenges and approaches

Agrawal, Jharna; Gupta, Manish Kumar; Garg, Hitendra

doi:10.1007/s11042-023-14649-x

Cited by 8 publications

(5 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various supervised deep-learning-based speech separation approaches have been proposed, yielding significant performance improvements [4]. [15] proposed a separation-mask method for speaker-dependent scenarios, where inference was conducted on mixed speech from only the speakers seen during training.…”

Section: Related Workmentioning

confidence: 99%

“…Conv-TasNet is an algorithm that receives the mixture waveform as input and uses the separation-mask method with speaker-independent scenarios supported by µPIT. Like the methods above, it achieved state-of-the-art separation performance in the past [4]. Dual-path RNN also uses the mixture waveform as input and adopts a doublecross RNN structure in the separation block [19].…”

Section: Related Workmentioning

confidence: 99%

“…Equation ( 5) is regarded as optimizing a single speech separation problem, where all model parameters, including D, b, Sep, and Dec, can be updated and learned via backpropagation in an end-to-end manner. The single problem is constructed by embedding the ML-ISTA forwarding calculation (2) into (5) through (4). The original problem to be solved is a bi-level optimization problem that consists of ( 5) and (1).…”

Section: Combining Conv-tasnet and Ml-istamentioning

confidence: 99%

“…However, these approaches have not yet reached the levels of separation capability of auditory systems. The challenge of the need for continuous improvement in the separation performance is pointed out in [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Leveraging Sparse Approximation for Monaural Overlapped Speech Separation From Auditory Perspective

Sekiguchi,

Narusue,

Morikawa

2023

IEEE Access

View full text Add to dashboard Cite

Neuroscience suggests that the sparse behavior of a neural population underlies the mechanisms of the auditory system for monaural overlapped speech separation. This study investigates leveraging sparse approximation to improve speech separation in a conventional deep learning algorithm. We develop a combined model that embeds a sparse approximation algorithm, a multilayered iterative soft thresholding algorithm (ML-ISTA), into a conventional time-domain-based speech separation algorithm, Conv-TasNet. Adopting ML-ISTA is a crucial enabler for the embedding process and helps avoid solving a bi-level optimization problem comprising sparse approximation and speech separation. ML-ISTA performs sparse approximation through forward calculations, thereby eliminating the optimization of sparse approximation. The combined model is trained with WSJ0-2mix, the Wall Street Journal English corpus for two-speaker mixed speech without noisy or reverberant interference, to clarify the proposed method's performance. The model demonstrates that sparse approximation improves separation performance regardless of the approximation setting. The peak performance of the model exceeds that of Conv-TasNet by 1.1% to 4.7% in four speech quality criteria. Moreover, sparse approximation accelerates the combined model performance gain at the early stages of learning relative to Conv-TasNet. The primary novelty of the study is embedding the sparse approximation algorithm, ML-ISTA, into a deep-learning-based speech separation framework and the experimental proof of improved separation performance in the proposed algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Combining Conv-tasnet and Ml-istamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Leveraging Sparse Approximation for Monaural Overlapped Speech Separation From Auditory Perspective

Sekiguchi,

Narusue,

Morikawa

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Typical techniques, which have achieved considerable success in addressing the BSS problem, include but are not limited to independent component analysis (ICA) and its variations [9,10], sparse component analysis (SCA) [7,11,12], sparse bounded component analysis (SBCA) [13], and non-negative matrix factorization (NMF) [14,15]. Recently, there has been an increasing interest in deep learning-based data-driven approaches [16,17]. Among these techniques, sparsity-based methods [18][19][20][21][22] have been extensively utilized due to their versatility in various situations for both (over)determined and underdetermined mixtures.…”

Section: Introduction 1backgroundmentioning

confidence: 99%

Exploiting Time–Frequency Sparsity for Dual-Sensor Blind Source Separation

Chen,

Zhang,

Sun

2024

Electronics

View full text Add to dashboard Cite

This paper explores the important role of blind source separation (BSS) techniques in separating M mixtures including N sources using a dual-sensor array, i.e., M=2, and proposes an efficient two-stage underdetermined BSS (UBSS) algorithm to estimate the mixing matrix and achieve source recovery by exploiting time–frequency (TF) sparsity. First, we design a mixing matrix estimation method by precisely identifying high clustering property single-source TF points (HCP-SSPs) with a spatial vector dictionary based on the principle of matching pursuit (MP). Second, the problem of source recovery in the TF domain is reformulated as an equivalent sparse recovery model with a relaxed sparse condition, i.e., enabling the number of active sources at each auto-source TF point (ASP) to be larger than M. This sparse recovery model relies on the sparsity of an ASP matrix formed by stacking a set of predefined spatial TF vectors; current sparse recovery tools could be utilized to reconstruct N>2 sources. Experimental results are provided to demonstrate the effectiveness of the proposed UBSS algorithm with an easily configured two-sensor array.

show abstract