引导式测验 · 中等 等级
FastSpeech 和非自回归 TTS 测验
检查并行频谱图生成、持续时间扩展、FastSpeech 2 音调和能量调节以及推理权衡。
问题 1 的 8
在 FastSpeech 上下文中“非自回归”是什么意思?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- 在 FastSpeech 上下文中“非自回归”是什么意思?
- 它并行而不是顺序生成所有频谱图帧
- 它按顺序一次生成一个音频帧
- 它无法处理长句子
- 它不需要训练数据
- FastSpeech 具体解决了 Tacotron 2 这样的自回归模型的哪些问题?
- 无法产生任何音频
- 生成缓慢,由于注意力错误而跳过或重复单词
- 缺乏对英文文本的支持
- 需要量子硬件
- FastSpeech 中“长度调节器”的作用是什么?
- 它压缩最终的音频文件
- 它消除了录音中的静音
- 它根据预测的持续时间重复每个音素的表示以匹配音频长度
- 它将音素翻译成文本
- Which additional speech variations does FastSpeech 2 condition on during training and inference?
- Only speaker age and recording location
- Video frames and subtitle color
- A single fixed global loudness value
- Pitch, energy, and duration information
- 为什么 FastSpeech 的推理时间几乎不随句子长度增长?
- 所有帧都是并行生成的,而不是顺序生成的
- 它忽略大部分输入文本
- 它只输出一秒的剪辑
- 它使用预先录制的句子的查找表
- How does the length regulator use predicted durations in FastSpeech?
- It selects the final audio codec
- It expands phoneme-level representations to align with the target spectrogram length
- It estimates the speaker’s identity from video
- It converts text into a sequence of labels for translation
- What is one tradeoff of non-autoregressive spectrogram generation?
- It guarantees identical prosody to an autoregressive model
- It removes the need for a waveform vocoder
- Parallel output can be faster, but duration and speech variation must be modeled explicitly
- It cannot accept text as input
- What training target does FastSpeech 2 use instead of FastSpeech’s teacher-generated simplified outputs?
- Only predicted durations with no acoustic target
- A translated text transcript
- The output of a GAN discriminator only
- Ground-truth target speech representations