similar to: need speech and music in one

Hi I am Rupesh from India. I have a huge directory of size 93.5 gb with 8500 mp3 files and 2000 sub directories. All these mp3s are speeches recorded by someone at 64 kbps. I want to compress these files recursively to opus using lame or another tool with 16 kbps bit rate and 11050 sample rate. I have compressed the above huge directory with above options using ffmpeg and the resulted

Hi, I have a question regarding the stereo capabilities of Opus. I would like to establish a connection between two ends via Wi-Fi and the signals that are to be transmitted are of speech kind. It mean on both ends speech is both recorded and played back as stereo. Now would the delay and loss characteristics of the speech transmission at a certain bitrate be the same as Mono voice transmission?

I had lunch with an interesting guy who had gotten .com-money to record the whole bible professionally with good actors (in swedish and english, kjv). The idea was to sell custom made compilations of biblical texts on cd over internet. The company is now out of money (surprise!), but all the material is recorded (about 350 hours) and if anyone gets a good idea on what to use the material to, it

On Fri, 6 Apr 2001, John Griffiths wrote: > ok so 24kbps for 56k modems... > > can i go any lower and get the 28 k modems? (still a lot of them about) or will 24 be good enough fo that? As others have said, 16kbps should do the trick. Keep in mind though that the quality of the sound will also depend on the sampling rate. MP3 will handle some higher sampling rates higher than some of

It is commonly said here that if I want to make AM radio-quality stuff at very low bitrates, a good way is to downsample. I downsampled a song to 11025Hz mono and encoded with -q 0, the result is about 18kbps and is at least radio quality. The downsampler I used is from Edinburgh speech tools, named ch_wave. `sox' performs terribly, so I didn't use it. However, I heard some unpleasant

Hello, I am studying different VAD (and Speech/Music detection) methods and find the one based on GRU very interesting (the one implemented in Opus 1.3). Is there a documentation on how to calculate the vector of input features [25 elements] and a description on how the GRU was trained (RFC, Presentation, ...etc.)? (I am not able to understand all the content of the source code in analysis.c )

Hi, (this is my first post here) A previous thread, starting Date: Tue 19 Nov 2002 - 06:09:56 EST "[vorbis] need speech and music in one" http://www.xiph.org/archives/vorbis/200211/0142.html expressed needs similar to mine, to encode a lengthy speech at low bitrate. I did some tests initially in September then concluded in December, and I was surprised to find Vorbis to be the best

Hi, I’m wondering how can I get the speech/music classification result when encoding the audio in opus 1.3.1? I found in the file opus_encoder.c, there is a opus_encoder_ctl request as OPUS_GET_VOICE_RATIO_REQUEST, so I wrote in my program the below code: #define OPUS_GET_VOICE_RATIO(x) 11019, __opus_check_int_ptr(x) int32_t voiceRatio; opus_encoder_ctl(encoder,

Father of groom speeches which bring about laughs in the faces of people listening are thought of to be one of the greatest things in attending any wedding affair. All weddings are understood as time for enjoyment. The joining of two hearts by means of wedding rituals also implies the unification of two families. And so, the best way to make the wedding a lot more special is presenting a father of

Hi, I am trying to encode raw wave data stored in a buffer using the Speex API (The raw wave data is created using the waveIn* functions - probably irrelevant information here). It is a 5 second clip, 16bits/sample, 8000Hz mono (which gives a buffer size of 80kb for the wave data). I have followed the exact procedure found in the manual available from the web site, except that

I know speex is not supposed to do a great job compressing music, but I've noticed that the new VBR code chokes completely when you try to compress horns. I've placed a particularly offensive example up at http://www.utdallas.edu/~matthias/ . Take a look at a-16m*{ogg,spx}. a.ogg is the first minute of an ogg created from the source media (in 44khz stereo). The rest have been mixed down

Please consider using 16-bit 16kHz (wideband) instead. It's a huge increase in audio quality and the bitrate is still very low, especially if you take advantage of Speex features such as VBR. 8kHz seems totally inappropriate to me for desktop streaming audio, let alone 8-bit samples. Or perhaps your recording equipment is an original Sound Blaster from 1989? (Even that could record at

Briefly: I want to be able to have "press or say (number)", with Asterisk listening for a spoken number, but accepting a DTMF digit, too. I'm posting everything I found so far, here, partly to show working, but also in case anyone else finds it useful. So, moving on.... This looked hopeful for a moment until I realised that it doesn't do DTMF:

Hi Reed, I've been using Speex to transmit TTS for years. It works very well with no tweaking. I use Microsoft TTS ("Microsoft Mike") with Speex at 16kHz wideband and VBR quality 6. Sometimes I forget that the sound is even coming from another computer and being compressed+decompressed. If anything, TTS seems easier for Speex to deal with than real voice. But I don't

On Mon, 2003-08-25 at 17:04, W. Kevin Pedigo wrote: > But if your problem is serving more bandwidth than you've got, you gotta > serve less (narrower or fewer streams) or get more bandwidth. It's that > simple. Tell us what you want to do about it, and we'll try to help. OK. I've gotten everything running with one problem. I'd like to downsample a live stream.

While I read on some other mailing list that the human ear is a poor testing device, it is still a widely available testing device and I often don't have anything better. In order to help that device better detect sound quality issues, I tend to prefer to use lengthy music files. Once I'm familiar enough with the music I can sense "something is wrong" with relatively little

Boink wrote: > They're streaming only in 22050/11khz mono. > I'm doing my stream around 30 kbps/11khz in *stereo*. Just my opinion but I've found streaming with quality -1 22khz Mono produces the best sound quality for 32kb/s. 11khz stereo sounds like crap in comparison. I'm just waiting (impatiently) for OddCastDSP(v1) to support 22050 mono via the SQRSoft crossfader. If

Well, some University in America (Rice University) has beginning a process of providing courses and books under CC licenses. I've looked into it and already found some interesting stuff that people in this list might found interesting. Frequency and Music An overview of frequency, harmonic (Fourier) series, and their relationship to music. http://cnx.org/content/col10338/latest/ Audio

Hi! Sorry for being somewhat offtopic but I'm hoping someone can help me. I need to download some music I can use in a one-time non-commercial multimedia presentation (technically speaking I'll be demo-ing ogg123 :-)). I don't care what it is, only it musn't suck and be somewhat suitable for general audience. RMS's speeches simply don't cut :-) So far all music I found on

Hi, Sorry to be posting about a subject that may have already been answered. If so, please point me in the right direction. I'm developing a dictation application on the Dell Axim (Windows Mobile 5.0 Pocket PC). A key requirement of the application is the best possible sampling rate as the audio goes into a speech reco system. So, I've set up my wrapper around libspeex to capture audio