腾讯云--- 音频语音识别/理解算法高级工程师
Tencent
腾讯云--- 音频语音识别/理解算法高级工程师
Job Description
腾讯云--- 音频语音识别/理解算法高级工程师
📋 Job Overview
The role of Senior Audio Speech Recognition/Understanding Algorithm Engineer at Tencent Cloud focuses on advancing speech recognition technologies for multilingual applications and efficient on-device implementations. Responsibilities include optimizing ASR effects, integrating large models with ASR, and tracking cutting-edge audio processing solutions. This position drives innovation in voice AI to enhance recognition accuracy and efficiency across diverse languages and scenarios.
📍 Location: Shenzhen, China
🏢 Business Unit: CSIG
📄 Full Description
2.负责语音识别asr-llm大模型与前沿技术调研与落地，比如更合理的语音与文本对齐、适用于多语种的模型方案、更高效的弱监督数据筛选流程等；
3.负责跟踪并复现业界最前沿的音频处理方案，并能融合优化当前效果。
🎯 Key Responsibilities
- Responsible for effect tuning and implementation in ASR applications, such as multilingual speech recognition and translation (Chinese/English/French/Japanese/Korean/Southeast Asia/Middle East), on-device super lightweight efficient ASR deployment, solving target speaker enhancement ASR technologies, acoustic/semantic VAD, etc.
- Responsible for research and implementation of ASR-LLM large models and frontier technologies, such as more reasonable speech-text alignment, multilingual model solutions, more efficient weak supervision data screening processes, etc.
- Responsible for tracking and reproducing the most advanced audio processing solutions in the industry, and integrating and optimizing current effects.
🛠️ Required Skills
- Expertise in speech recognition (ASR) technologies
- Experience with multilingual speech processing and translation
- Knowledge of on-device lightweight ASR implementation
- Skills in target speaker enhancement and VAD (Voice Activity Detection)
- Proficiency in large language models (LLM) integration with ASR
- Ability to conduct frontier technology research and reproduction
- Audio processing and optimization techniques
Locations
- Shenzhen, China
Salary
300,000 - 600,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Expertise in speech recognition (ASR) technologiesintermediate
- Experience with multilingual speech processing and translationintermediate
- Knowledge of on-device lightweight ASR implementationintermediate
- Skills in target speaker enhancement and VAD (Voice Activity Detection)intermediate
- Proficiency in large language models (LLM) integration with ASRintermediate
- Ability to conduct frontier technology research and reproductionintermediate
- Audio processing and optimization techniquesintermediate
Responsibilities
- Responsible for effect tuning and implementation in ASR applications, such as multilingual speech recognition and translation (Chinese/English/French/Japanese/Korean/Southeast Asia/Middle East), on-device super lightweight efficient ASR deployment, solving target speaker enhancement ASR technologies, acoustic/semantic VAD, etc.
- Responsible for research and implementation of ASR-LLM large models and frontier technologies, such as more reasonable speech-text alignment, multilingual model solutions, more efficient weak supervision data screening processes, etc.
- Responsible for tracking and reproducing the most advanced audio processing solutions in the industry, and integrating and optimizing current effects.
Tags & Categories
Answer 10 quick questions to check your fit for 腾讯云--- 音频语音识别/理解算法高级工程师 @ Tencent.
Related Books and Jobs
腾讯云--- 音频语音识别/理解算法高级工程师
Tencent
腾讯云--- 音频语音识别/理解算法高级工程师
Job Description
腾讯云--- 音频语音识别/理解算法高级工程师
📋 Job Overview
The role of Senior Audio Speech Recognition/Understanding Algorithm Engineer at Tencent Cloud focuses on advancing speech recognition technologies for multilingual applications and efficient on-device implementations. Responsibilities include optimizing ASR effects, integrating large models with ASR, and tracking cutting-edge audio processing solutions. This position drives innovation in voice AI to enhance recognition accuracy and efficiency across diverse languages and scenarios.
📍 Location: Shenzhen, China
🏢 Business Unit: CSIG
📄 Full Description
2.负责语音识别asr-llm大模型与前沿技术调研与落地，比如更合理的语音与文本对齐、适用于多语种的模型方案、更高效的弱监督数据筛选流程等；
3.负责跟踪并复现业界最前沿的音频处理方案，并能融合优化当前效果。
🎯 Key Responsibilities
- Responsible for effect tuning and implementation in ASR applications, such as multilingual speech recognition and translation (Chinese/English/French/Japanese/Korean/Southeast Asia/Middle East), on-device super lightweight efficient ASR deployment, solving target speaker enhancement ASR technologies, acoustic/semantic VAD, etc.
- Responsible for research and implementation of ASR-LLM large models and frontier technologies, such as more reasonable speech-text alignment, multilingual model solutions, more efficient weak supervision data screening processes, etc.
- Responsible for tracking and reproducing the most advanced audio processing solutions in the industry, and integrating and optimizing current effects.
🛠️ Required Skills
- Expertise in speech recognition (ASR) technologies
- Experience with multilingual speech processing and translation
- Knowledge of on-device lightweight ASR implementation
- Skills in target speaker enhancement and VAD (Voice Activity Detection)
- Proficiency in large language models (LLM) integration with ASR
- Ability to conduct frontier technology research and reproduction
- Audio processing and optimization techniques
Locations
- Shenzhen, China
Salary
300,000 - 600,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Expertise in speech recognition (ASR) technologiesintermediate
- Experience with multilingual speech processing and translationintermediate
- Knowledge of on-device lightweight ASR implementationintermediate
- Skills in target speaker enhancement and VAD (Voice Activity Detection)intermediate
- Proficiency in large language models (LLM) integration with ASRintermediate
- Ability to conduct frontier technology research and reproductionintermediate
- Audio processing and optimization techniquesintermediate
Responsibilities
- Responsible for effect tuning and implementation in ASR applications, such as multilingual speech recognition and translation (Chinese/English/French/Japanese/Korean/Southeast Asia/Middle East), on-device super lightweight efficient ASR deployment, solving target speaker enhancement ASR technologies, acoustic/semantic VAD, etc.
- Responsible for research and implementation of ASR-LLM large models and frontier technologies, such as more reasonable speech-text alignment, multilingual model solutions, more efficient weak supervision data screening processes, etc.
- Responsible for tracking and reproducing the most advanced audio processing solutions in the industry, and integrating and optimizing current effects.
Tags & Categories
Answer 10 quick questions to check your fit for 腾讯云--- 音频语音识别/理解算法高级工程师 @ Tencent.
Related Books and Jobs