AI/ML Based Audio Classification and Transcription for Automotive and Off-Highway Systems Cyient, Limited

Format:

Book

Conference/Event

Author/Creator:

Singh, Shwetha, author.

Contributor:

Kalidas, Sateesh

Kamble, Amit

Mohanty, Ananta

Conference Name:

Off-Highway Technical Conference 2025 (2025-11-06 : Pune, India)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2025

Summary:

Modern automotive systems generate a wide range of audio-based signals, such as indicator chimes, turn signals, infotainment system audio, navigation prompts, and warning alerts, to facilitate communication between the vehicle and its occupants. Accurate Classification and transcription of this audio is important for refining driver aid systems, safety features, and infotainment automation. This paper introduces an AI/ML-powered technique for audio classification and transcription in automotive environments. The proposed solution employs a hybrid deep learning architecture that leverages convolutional neural networks (CNNs) and recurrent neural networks (RNNs), trained using labeled audio samples. Moreover, an Automatic Speech Recognition (ASR) model is integrated for transcribing spoken navigation prompts and commands from infotainment systems. The proposed system delivers reliable results in real-time audio classification and transcription, facilitating better automation and validation. Additionally, we highlight the potential applications of this technology for test automation in automotive software validation. This solution is well-suited for application in transportation systems, surveillance and security, accessibility tools for the hearing impaired, smart home assistants, humanoid robots, and others, making it highly versatile across various domains and platforms. This provides a robust foundation for edge-deployable audio intelligence systems. Beyond Off-highway applications, it applies broadly across other domains where contextual audio understanding is essential--such as in edge-based surveillance systems, supportive accessibility technologies, smart home ecosystems, and self-driving robots. By merging distinctive audio features with state-of-the-art speech transcription, this framework establishes the foundation for scalable and deployable edge-AI systems capable of smart auditory perception across embedded platforms

Notes:

Vendor supplied data

Publisher Number:

2025-28-0323

Access Restriction:

Restricted for use by site license