Binaural sound source localisation and tracking using a dynamic spherical head model

Schymura, Christopher; Winter, Fiete; Kolossa, Dorothea; Spors, Sascha

doi:10.21437/interspeech.2015-77

Cited by 6 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, random head movements yield no significant improvements with respect to the baseline throughout all conducted experiments. This effect is similar to the results described in [8], where it was shown that control strategies based on a feed-forward paradigm are not as beneficial for localization performance as closed-loop feedback control.…”

Section: Resultssupporting

confidence: 89%

“…Two different head rotation schemes and their effect on localization and segregation performance are investigated in this study. They are partially adopted from previous work presented in [8].…”

Section: Feedback Through Rotational Head Movementsmentioning

confidence: 99%

“…However, various psychophysical studies have shown that the human auditory system incorporates additional top-down knowledge while assessing auditory scenes [2]. This has lead to some recent developments in the field of machine hearing, where various models that integrate top-down feedback into their processing path have been proposed [6,7,8].…”

Section: Introductionmentioning

confidence: 99%

“…Top-down feedback in machine hearing systems has especially been exploited in the context of binaural localization. Recent studies focus on statistical models [6], deterministic approximations of head related transfer functions (HRTFs) [8] and deep neural networks (DNNs) [7] to map interaural time differences (ITDs) and interaural level differences (ILDs) to the corresponding angular sound directions. By incorporating head movements, these models achieve superior localization perfor-mance compared to the static case.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Active Machine Hearing System for Auditory Stream Segregation

Schymura¹,

Walther²,

Kolossa³

2016

Preprint

Self Cite

View full text Add to dashboard Cite

This study describes a binaural machine hearing system that is capable of performing auditory stream segregation in scenarios where multiple sound sources are present. The process of stream segregation refers to the capability of human listeners to group acoustic signals into sets of distinct auditory streams, corresponding to individual sound sources. The proposed computational framework mimics this ability via a probabilistic clustering scheme for joint localization and segregation. This scheme is based on mixtures of von Mises distributions to model the angular positions of the sound sources surrounding the listener. The distribution parameters are estimated using block-wise processing of auditory cues extracted from binaural signals. Additionally, the proposed system can conduct rotational head movements to improve localization and stream segregation performance. Evaluation of the system is conducted in scenarios containing multiple simultaneously active speech and non-speech sounds placed at different positions relative to the listener.

show abstract

Section: Resultssupporting

confidence: 89%

Section: Feedback Through Rotational Head Movementsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Active Machine Hearing System for Auditory Stream Segregation

Schymura¹,

Walther²,

Kolossa³

2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ma et al proposed a method that considers maximum three simultaneous speakers in two different reverberant rooms, and three azimuth head rotation strategies limited to the ±90º range [58]. A similar approach studied the same head rotation interval with sound sources placed at 3 m from the receiver and five possible azimuth angles [59]. Another study increased the number of rooms to 4, but reduced the rotation interval to ±60º for training and ±30º for testing [60].…”

Section: Binaural Doae With Head Rotation or A Moving Listenermentioning

confidence: 99%

Binaural Sound Source Distance Estimation and Localization for a Moving Listener

Krause,

García-Barrios,

Politis

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In this paper, we investigate the tasks of binaural source distance estimation (SDE) and direction-of-arrival estimation (DOAE) using motion-based cues in a scenario with a walking listener. On top of performing both tasks as separate problems, we study two methods of solving the joint task of simultaneous source distance estimation and localization (SDEL), with a single model. Experiments are conducted for three different scenarios: a static receiver; a static receiver with a rotating head; and a freely moving listener inside a room. The study proposes rotation and translation features to include information about the receiver's motion during model training and studies the effects of these on the final performance. The work includes extended simulation of three datasets containing numerous testing scenarios for sound sources, covering a wide range of DOAs and a source-to-receiver distance up to 15 m. Results are further analyzed with respect to room reverberation, walking speed, as well as source-to-receiver distance. The presented outcomes show large improvements in both DOA and distance estimation for a model that uses motion-based cues as compared with a static scenario. These include a decrease of 9.50°in DOA and 1.56m in distance errors for a joint model, followed by 16.17°and 0.17m for separate models.

show abstract

Towards modelling active sound localisation based on Bayesian inference in a static environment

et al. 2021

View full text Add to dashboard Cite

Over the decades, Bayesian statistical inference has become a staple technique for modelling human multisensory perception. Many studies have successfully shown how sensory and prior information can be combined to optimally interpret our environment. Because of the multiple sound localisation cues available in the binaural signal, sound localisation models based on Bayesian inference are a promising way of explaining behavioural human data. An interesting aspect is the consideration of dynamic localisation cues obtained through self-motion. Here we provide a review of the recent developments in modelling dynamic sound localisation with a particular focus on Bayesian inference. Further, we describe a theoretical Bayesian framework capable to model dynamic and active listening situations in humans in a static auditory environment. In order to demonstrate its potential in future implementations, we provide results from two examples of simplified versions of that framework.

show abstract

Binaural sound source localisation and tracking using a dynamic spherical head model

Cited by 6 publications

References 21 publications

An Active Machine Hearing System for Auditory Stream Segregation

An Active Machine Hearing System for Auditory Stream Segregation

Binaural Sound Source Distance Estimation and Localization for a Moving Listener

Towards modelling active sound localisation based on Bayesian inference in a static environment

Contact Info

Product

Resources

About